Hastings Greer will present the paper “Scoliosis Screening and Monitoring Using Self Contained Ultrasound and Neural Networks.” His co-authors include Samuel Gerber, Matthew McCormick, Deepak Chittajallu, Neal Siekierski, Matthew Oetgen, Kevin Cleary and Stephen Awylward.

Aylward will speak at the session on Imaging for Developing Countries. He will discuss “Computer-augmented Point-of-care Ultrasound Technologies and Applications,” which he co-authored.

Alyward is also a co-author on the paper “Next-generation Ultrasound Imaging for Assessing the Microvascular Fingerprint of Cancer.” It will be presented in the session on Ultrasonic Imaging-Based Tissue Characterization.

The paper “Vectorized persistent homology representations for characterizing glandular architecture in histology images” also discusses the use of image analysis in the detection of cancer. Deepak Chittajallu will present the work, which he completed with Neal Siekierski, Sanghoon Lee, Samuel Gerber, Jonathan Beezley, David Manthey, David Gutman and Lee Cooper.

Andinet Enquobahrie will be part of the panel VR/AR for Surgery and Medical Education, which will occur from 1:30 to 2:30 p.m. PST. The panel will feature researchers and clinicians who develop virtual simulators for medical applications.

Andinet Enquobahrie will highlight virtual trainers for laparoscopic surgery.

Kitware’s Senior Director of Computer Vision, Dr. Anthony Hoogs, is an invited speaker at this year’s 2018 SPIE Defense + Security Conference in Orlando, FL, April 15-19, which is a part of the Defense + Commercial Sensing Conference.

Event Details:

The Defense + Commercial Sensing Conference is a global event combining the SPIE Defense + Security Conference and the Commercial + Scientific Sensing and Imaging Conference, which will provide a wealth of information on sensing, imaging, and photonic technologies for professionals in defense and industry, as well as academics.   The SPIE Defense + Security Conference focuses on sensors, imaging, and optical technologies for security, law enforcement, avionics/aerospace, autonomous systems, defense, health care, and military applications. This year their focus is on “Sensing and imaging research for a safer world” and will also include commercial sensing with two technical programs with 1,900 presentations, a 400-company expo, and 34 courses focused on training and education.  Information related to the latest technical advances in sensors, infrared technology, laser systems, spectral imaging, radar, LiDAR and more will be provided in various venues throughout this five-day event. Make sure to check out the most recent Defense + Commercial Sensing Program for the list of events.

Details:

Kitware’s Senior Director of Computer Vision, Anthony Hoogs, Ph.D., is an invited speaker for the Panel Discussion titled “Machine Learning for Automatic Target Recognition (ML4ATR)”.  Anthony will provide insight into Kitware’s research and technology development on programs related to machine learning for Automatic Target Recognition (ATR). This two hour panel begins on Monday, April 16th at 10:30 am in conference room 10648 and will highlight the accomplishments and challenges in designing and deploying deep learning and big data analytics algorithms, systems, and hardware for ATR.  An array of professionals with in-depth experience related to ATR will present information related to projects on machine learning for ATR representing defense, industry, and research labs. Topics of interest include but are not limited to training deep learning based ATR with limited measured/real data, change detection, patterns-of-life analysis, and multi-modal satellite/hyperspectral/Sonar/Full Motion Video (FMV) analytics.  This panel provides a forum for program managers, researchers, practitioners, and software engineers and scientists across various disciplines of ATR to connect, engage, learn, and shape the future of this field. Make sure to keep an eye out on the program for any schedule changes so as not to miss the informative panel.

Kitware’s Computer Vision group recognizes how valuable advancing computer vision and deep learning is in order to greatly improve and push capabilities beyond their limits supporting the DoD and Intelligence Communities as well as Industry and Academia.  Our main focus areas include deep learning, object detection and tracking, image and video scene understand, image and video forensics, social multimedia analysis, complex activity, event, and threat detection, 3D vision, and super resolution; however we are not limited and continuously explore and participate in other research and development for our customers and our partners.  We have worked with various agencies, such as the Defense Advanced Research Project Agency (DARPA), Air Force Research Laboratory (AFRL), the Office of Naval Research (ONR), Intelligence Advanced Research Projects Activity (IARPA) and the U.S. Air Force. Kitware has developed and deployed an operational Wide Area Motion Imagery (WAMI) tracking systems for Intelligence, Surveillance, and Reconnaissance (ISR) in theatre, providing analysts with exploitation capabilities that fuse sensors, platforms, and people.  Our work with DARPA on Squad-X has led to extensive research, development, and deployment of robust methods to more accurately identify and track objects and people, delivered straight to the soldier on the ground. In addition, Kitware is continually improving their KitWare Image and Video Exploitation and Retrieval (KWIVER) toolkit, which is an open source framework for video and image analytics built from Kitware’s years of experience developing analytic systems for various customers in multiple domains.  Please visit our computer vision and KWIVER webpages for more information into our key focus areas and experience.

Contact:

Please reach out to computervision@kitware.com to schedule meetings throughout this event.  Anthony Hoogs will be on-hand for in depth conversations. We are looking forward to engaging with this community and sharing information on Kitware’s ongoing research and capability development in computer vision, machine learning, and deep learning as well as our cutting-edge open source vision software, KWIVER.

Kitware will be at the GPU Technology Conference held March 26-29 in Silicon Valley CA.

Event Details:

This conference, hosted by NVIDIA is the premier conference on artificial intelligence and deep learning.  It showcases the latest breakthroughs from academia, government, startups and major enterprises in various industries such as government, healthcare, automotive & transportation, etc.  Technologies, researchers, and developers will be in attendance supporting top companies, government agencies, research firms, and universities from around the world. There will be hundreds of sessions focused on topics such as smart cities, autonomous machines, deep learning and artificial intelligence, HPC & supercomputing, accelerated analytics, developer tools.  Make sure to Browse Their Sessions and Explore Their Broad Range of Topics to familiarize yourself with this conference and the valuable information it will provide to its international audience.

Details:

Paul Tunison, a Senior R&D Engineer with Kitware’s Computer Vision team will be in attendance.  He has a wealth of experience in computer science and deep learning utilizing NVIDIA GPUs to improve processing, performance, and training models.  He has successfully contributed to various Kitware programs supporting our government, commercial, and academic customers and partners.

Kitware’s Computer Vision team recognizes how valuable advancing computer vision and deep learning is in order to greatly improve and push capabilities beyond their limits supporting our customers and collaborators.  The use of NVIDIA GPUs has greatly improved our performance in our key focus areas and provided a mechanism to continue to evolve our state-of-the-art algorithm and technology development. Our main focus areas include deep learning, object detection and tracking, image and video scene understand, image and video forensics, social multimedia analysis, complex activity, event, and threat detection, 3D vision, and super resolution; however we are not limited and continuously explore and participate in other research and development opportunities.  We use successful techniques to build advanced open source tools and capabilities focused on different applications to enhance and improve deep learning processing and training of models.

We have worked with various agencies, such as the Defense Advanced Research Project Agency (DARPA), Air Force Research Laboratory (AFRL), the Office of Naval Research (ONR), Intelligence Advanced Research Projects Activity (IARPA) and the U.S. Air Force.  Our work with DARPA on Squad-X has led to extensive research, development, and deployment of robust methods to more accurately identify and track objects and people, delivered straight to the soldier on the ground. On IARPA’s Deep Intermodal Video Analytics (DIVA) Program, Kitware is responsible for Test & Evaluation (T&E), which has provided us the opportunity to collect multi-camera datasets representing collections from a suite of surveillance camerasand we utilize NVIDIA GPUs to improve processing and deep learning training and testing.  We are developing an open source framework for underwater image and video analytics known as the Video and Image Analytics for a Marine Environment (VIAME) in cooperation with NOAA’s Automated Image Analysis Strategic Initiative (AIASI); where almost 50% of the operations are run on NVIDIA GPUs.  Kitware’s work on the Media Forensics (MediFor) Program applying deep learning to advanced techniques and algorithms to determine the digital, physical, and semantic integrity in visual media uses GPUs for processing to train and test deep networks for image and video forensic algorithms.   In addition to these projects, Kitware is continually improving their KitWare Image and Video Exploitation and Retrieval (KWIVER) toolkit, which is an open source framework for video and image analytics built from Kitware’s years of experience developing analytic systems for various customers in multiple domains.  Please visit our computer vision and KWIVER webpages for more information into our key focus areas and experience.

Contact:

Please reach out to computervision@kitware.com and/or paul.tunison@kitware.com to schedule meetings throughout this event.  Paul Tunison will be on-hand for in depth conversations. We are looking forward to engaging with this community and sharing information on Kitware’s ongoing research and capability development in computer vision and deep learning using GPUs; as well as our cutting-edge open source vision software, KWIVER.

Principal Engineer Matthew McCormick will give a talk titled “itk-jupyter-widgets: Interactive 3D and 2D Visualization in Jupyter.”

Kitware will be briefing at this year’s 2018 Military Sensing Symposia (MSS) Parallel Meeting under the MSS Specialty Group on Passive Sensors in Gaithersburg, MD, March 19-23.

Event Details:

This event is the annual parallel meeting of the MSS Specialty Group on Detectors, the MSS Specialty Group on Passive Sensors, the MSS Specialty Group on Materials and the MSS Specialty Group on Battlefield Survivability and Discrimination.  According to the MSS website, it will include five days of presentations, discussions, and dissemination of information on various technologies and capabilities related to each Group, all conducted at the SECRET classified level.  Sessions will include but are not limited to Image Processing and Real-Time Implementation, Multidimensional and Diversity Sensors, Sensor System Design & Development, Small Unattended Aircraft Systems (SUAS) Sensors and Systems, Emerging Technologies and System Concepts, and a Special Session on Passive MMW Imaging Through Degraded Visual Environment.  Make sure to check out their website for more details on the different Groups and to register by their deadline of March 3, 2018.  Various Department of Defense (DoD), Industry, Commercial, and Academic experts will be in attendance to collaborate and learn more about technology, capabilities, and needs.

Details:

Matt Leotta, Ph.D., a Team Principal and Technical Leader within the Computer Vision Group at Kitware, will speak on Telesculptor: Dense 3D Models from Uncalibrated Full Motion Video (FMV).  Accurate and dense 3D models are an important resource in mission planning for special operations.  Full Motion Video (FMV) is often readily available and up-to-date when active sensors data, such as lidar, are not.  Current techniques using FMV to produce 3D models are labor intensive and manual, and are not able to respond quickly to real-time operations and decision making.  The use of FMV to build accurate 3D models automatically is possible, and Kitware will present their recent work supported by the U.S. Air Force (USAF) to automate the reconstruction of accurate and dense 3D models from operational FMV.  Details addressing the challenges of applying structure from motion (SfM) and multi-view stereo (MVS) to FMV will be included, such as missing metadata, cloud cover, metadata “burned” into the video, etc.  Kitware’s approaches to overcome these challenges will be broken down and preliminary results will show that semantic segmentation of video key frames can be used to improve 3D results.  Experimental results showing detailed 3D models produced from FMV data collected by Air Force Special Operations Command (AFSOC) will demonstrate that fine scale details are visible, such as utility poles and tree trunks.  Fine scale details greatly improve mission planning, analysis of a scene, and accuracy.  Authors to this paper include Matt Leotta, Eric Smith, Ph.D., and David Russell, all with Kitware, Inc. and the Computer Vision Group.

Kitware’s Computer Vision group recognizes how valuable advancing computer vision and deep learning is in order to greatly improve and push capabilities beyond their limits supporting the DoD and Intelligence Communities.  We have worked with various agencies, such as the Defense Advanced Research Project Agency (DARPA), Air Force Research Laboratory (AFRL), the Office of Naval Research (ONR), Intelligence Advanced Research Projects Activity (IARPA) and the U.S. Air Force.  Kitware has developed and deployed an operational Wide Area Motion Imagery (WAMI) tracking systems for Intelligence, Surveillance, and Reconnaissance (ISR) in theatre, providing analysts with exploitation capabilities that fuse sensors, platforms, and people.  Our work with DARPA on Squad-X has led to extensive research, development, and deployment of robust methods to more accurately identify and track objects and people, delivered straight to the soldier on the ground. In addition, Kitware is continually improving their KitWare Image and Video Exploitation and Retrieval (KWIVER) toolkit, which is an open source framework for video and image analytics built from Kitware’s years of experience developing analytic systems for various customers in multiple domains.  KWIVER has grown to include our Motion-imagery Aerial Photogrammetry Toolkit (MAP-TK), an open source toolkit for making measurements from aerial video.  Kitware also provides an end-user application called TeleSculptor which uses KWIVER to  provide the 3D Model generation solution from FMV.  Please visit our computer vision and KWIVER webpages for more information into our key focus areas and experience.

Contact:

Please reach out to computervision@kitware.com to schedule meetings throughout this event.  Matt Leotta will be on-hand for in depth conversations.  We are looking forward to engaging with this community and sharing information on Kitware’s ongoing research and capability development in computer vision and deep learning as well as our cutting-edge open source vision software, KWIVER.

This event is organized by the Laboratory for Computational Sensing and Robotics at Johns Hopkins University. As a member of the external advisory board for the laboratory, Senior Director of Strategic Initiatives Stephen Aylward will conduct interviews at the event. To schedule an interview, please email kitware@kitware.com.

Kitware will present three free, one day training courses next month at our Albany, NY headquarters.

March 15‘th “CMake and Friends”
all day: w/ Bill Hoffman

To reserve a seat for the course, please fill out this google form and we’ll get back to you to confirm your reservation. https://goo.gl/forms/M3WmJcV9W6qKTK8x2

Kitware is sponsoring this year’s 18th IEEE Winter Conference on Applications of Computer Vision (WACV) in Lake Tahoe, CA, March 12-14. In addition, Anthony Hoogs, Ph.D., the Senior Director of Computer Vision at Kitware, is a General Co-Chair and is on the Steering Committee.

Event Details:

This year’s WACV18 is the largest WAVC to date; jointly sponsored by the IEEE Society and the IEEE Biometrics Council.  Each year WACV continues to grow with active participation by academia, industry, and government representatives. The event’s combination of workshops, tutorials and main sessions all focus on providing in-depth information on cutting edge research advances in applications of computer vision technology.  Topics such as biometrics, deep learning, action recognition, surveillance, 3D reconstruction, tracking, detection, and vision and learning will be discussed in various formats such as presentations, poster sessions, and forums. This venue promotes collaboration, research and development, and insight into computer vision applications and technology.  Make sure to look at the recently published WACV18 program schedule for the list of events.

Details:

Kitware is a Silver Sponsor at this year’s WACV18.  Kitware sponsors this conference each year to support this community, recruit computer vision professionals, and to continue collaboration and engagement.  Anthony Hoogs, Ph.D., the Senior Director of Computer Vision at Kitware, is a General Co-Chair and is on the Steering Committee; serving WACV from a professional, intellectual, and organizational standpoint in order to help plan, organize, and cultivate the best environment for this community.  Kitware has a long-standing presence and level of participation at WACV as computer vision and deep learning are key elements to furthering advanced application development for various industries and for Kitware.

Kitware’s Computer Vision group recognizes how valuable advancing computer vision and deep learning is in order to greatly improve and push capabilities beyond their limits supporting academia, industry, and the DoD and Intelligence Communities.  Our main focus areas include deep learning, object detection and tracking, image and video scene understanding, image and video forensics, social multimedia analysis, complex activity, event, and threat detection, 3D vision, and super resolution. However, we are not limited and continuously explore and participate in other research and development for our customers and our partners.  We partner with many academic institutions such as Harvard, Massachusetts Institute of Technology, Cornell University, University of California, Berkley, and Texas A&M University. We have worked with various agencies, such as the Defense Advanced Research Project Agency (DARPA), Air Force Research Laboratory (AFRL), the Office of Naval Research (ONR), Intelligence Advanced Research Projects Activity (IARPA) and the U.S. Air Force.  Kitware has developed and deployed an operational Wide Area Motion Imagery (WAMI) tracking systems for Intelligence, Surveillance, and Reconnaissance (ISR) in theatre, providing analysts with exploitation capabilities that fuse sensors, platforms, and people. Our work with DARPA on Squad-X has led to extensive research, development, and deployment of robust methods to more accurately identify and track objects and people, delivered straight to the soldier on the ground.  In addition, Kitware is continually improving their KitWare Image and Video Exploitation and Retrieval (KWIVER) toolkit, which is an open source framework for video and image analytics built from Kitware’s years of experience developing analytic systems for various customers in multiple domains.  Please visit our computer vision and KWIVER webpages for more information into our key focus areas and experience.

Contact:

Please reach out to computervision@kitware.com to schedule meetings throughout this event.  Anthony Hoogs will be on-hand for in depth conversations. We are looking forward to engaging with this community and sharing information on Kitware’s ongoing research and capability development in computer vision and deep learning as well as our cutting-edge open source vision software, KWIVER.

Kitware will present research in maritime video analytics at the Second Annual Workshop on Naval Applications of Machine Learning (NAML) at SPAWAR in San Diego, CA, February 13-15.

Event Details:

The second annual workshop on NAML is a three day event with oral and poster presentations focused on autonomy, computer vision and cybersecurity for the Navy.  It will be held at the Topside location of SPAWAR Systems Center Pacific with participation from the Navy, Department of Defense (DoD) and intelligence communities, as well as industry and academia.  According to the NAML website, the goals of this conference are to spread awareness of current machine learning research relevant to Navy applications, to connect machine learning researchers with experts in Navy needs and requirements, and to build and strengthen collaborations within the DoD research community.  Check out their website for more details and for the full agenda, which will be released soon.

Details:

Dr. Arslan Basharat, a Technical Leader in the Computer Vision Group at Kitware will speak about Small Target Detection using a Spatiotemporal Autoencoder.  This presentation will discuss methods Kitware uses to detect small targets, such as a boat or vessel, in aerial video collected from a distance on open water.  An unsupervised approach will be used to learn the visual appearance and dynamics of open water under various sea states, illumination conditions and viewing angles.  Using hours of videos of open water, Kitware is able to perform unsupervised training in order to address this challenging technical problem.  Be sure to regularly check in on the NAML website for an updated full agenda in order to attend this technical presentation.

Kitware’s Computer Vision group recognizes the value of advancing computer vision and deep learning in order to push capabilities beyond the state-of-the-art in supporting the Navy, DoD, Intelligence, and Law Enforcement communities.  We have worked with various agencies, such as the Defense Advanced Research Project Agency (DARPA), Air Force Research Laboratory (AFRL), the Office of Naval Research (ONR), and the Intelligence Advanced Research Projects Activity (IARPA).  Kitware has developed and deployed an operational Wide Area Motion Imagery (WAMI) tracking systems for Intelligence, Surveillance, and Reconnaissance (ISR) in theatre, providing analysts with exploitation capabilities that fuse sensors, platforms, and people.  Our work with DARPA on Squad-X has led to extensive research, development, and deployment of robust methods to more accurately identify and track objects and people, delivered straight to the soldier on the ground. In addition, Kitware is continually improving their KitWare Image and Video Exploitation and Retrieval (KWIVER) toolkit, which is an open source framework for video and image analytics built from Kitware’s years of experience developing analytic systems for various customers in multiple domains.  Please visit our computer vision and KWIVER webpages for more information into our key focus areas and experience.

Contact:

Please reach out to computervision@kitware.com to schedule meetings throughout this event.  Arslan Basharat will be on-hand for in depth conversations.  We are looking forward to engaging with this community and sharing information on Kitware’s ongoing research and capability development in computer vision and deep learning as well as our cutting-edge open source vision software, KWIVER.

Director of Medical Computing Andinet Enquobahrie, Staff R&D Engineer Jeff Webb, Staff R&D Engineer Aaron Bray, R&D Engineer Samantha Horvath and Business Development Representative Libby Rose will exhibit at booth 611.

Technical Leader Michael Grauer, Principal Engineer Jean-Christophe Fillion-Robin, Senior R&D Engineer Johan Andruejol, R&D Intern Laura Pascal, R&D Intern Pierre Assemat and R&D Intern Jean-Baptiste Vimort will participate.

Presentations

Slicer Shape AnaLysis Toolbox (SlicerSalt)

By Laura Pascal

The collaborative project has applications in dental and craniofacial research.

Girder and SlicerCLIs in the Cloud

By Michael Grauer

The project allows users to save a scene from 3D Slicer in Girder. It also allows users to integrate an authenticated RESTful application programming interface (API) with 3D Slicer.

OpenVR projects

By Jean-Christophe Fillion-Robin

The projects focus on finalizing the integration of HTC Vive with 3D Slicer, thanks to the OpenVR module in the Visualization Toolkit (VTK).

Senior Director of Strategic Initiatives Stephen Aylward will present this invited talk to members of the Sheikh Zayed Institute for Pediatric Surgery Innovation of Children’s National Health System.

Senior Director of Strategic Initiatives Stephen Aylward will present this invited talk to members of the department of radiology at Johns Hopkins University. The abstract is as follows:

For the full potential of point-of-care ultrasound to be realized, these systems must be approached as if they were new diagnostic modalities, not simply as inexpensive portable ultrasound imaging systems. These systems must incorporate automated data analysis algorithms, rugged hardware, and specialized interfaces to guide novice users to properly place and manipulate an ultrasound probe and interpret its outputs. Furthermore, the outputs of a point-of-care ultrasound system should be quantitative measures and easy-to-understand reformulations of the acquired data, not b-mode images. It should be assumed that the expertise needed to interpret b-mode images will not be readily available at a point of care, e.g., when used by emergency medical service personnel to triage trauma patients or when used in schools to screen for scoliosis. This talk will discuss those applications and others, as ongoing research projects in collaboration with JHU and several other academic and industry partners.

Figure 1. Reflection invariant feature matching between the scene and reflection regions by the Bag-of-Features approach. Left: Original color image. Right: Feature detection and matching on the corresponding image.

The 9th IEEE International Workshop on Information Forensics and Security (WIFS) is just around the corner and is being held December 4-7 in Rennes France, at INRIA Rennes-Bretagne-Atlantique.  This annual event, organized by the IEEE Information Forensics and Security (IFS) Technical Committee of the IEEE Signal Processing Society, brings together international researchers and technical experts from a range of relevant disciplines in order to brainstorm and exchange new ideas to address and discuss emerging challenges focused on Information Security.  The 4-day technical conference will be packed with keynote lectures, technical sessions and tutorials including but not limited to topics such as forensics analysis, multimedia security, biometrics, and cybersecurity.

Kitware has a paper in the main program of this highly selective workshop. On Thursday, December 7 from 0900-1030, in a session on Image Forensics, Dr. Anthony Hoogs, Kitware’s Senior Director of Computer Vision, will brief the audience on Object Insertion and Removal in Images with Mirror Reflection, by Dr. Harry Sun and Dr. Hoogs. In this day and age, the ability to manipulate photos to control content and messages to share though the internet, press, and social media has become a reality.  This type of manipulation can have serious negative impacts.  To circumvent these malicious actions, methods to determine whether or not this manipulation has occurred are needed.  Being able to detect photo manipulation, such as object insertion and removal, are key elements that can be used to accurately determine whether images have been altered.  Kitware will discuss their reflection integrity assessment for images with strong mirror reflections in order to detect when objects have been inserted in images or items have been removed.  By predicting reflection locations and geometry using scene content, and then comparing reflections with the objects that are directly observed in the images, inconsistencies can be detected indicating potential manipulation.  Kitware proposes a reflection-invariant Bag-of-Features approach to detect and match points of interest with no prior knowledge.   Anthony will provide technical details on these techniques and demonstrate Kitware’s experimental results, which have been validated on 868 images of real-world scenes. Zhaohui H. Sun, Ph.D., co-authored this paper with Anthony Hoogs and is a member of Kitware’s Computer Vision Group and a Senior Member of IEEE.  Make sure to keep an eye on the Program Schedule as the schedule is tentative at this time.

Figure 2. Left: manipulated images. Center: reflection-invariant feature matching. Right: changes of object removal and insertion.

Kitware’s Computer Vision Group specializes in cutting edge technologies and techniques utilizing computer vision deep learning in order to solve challenging video and image problems.  Our expertise developing robust capabilities such as image and video scene understanding, complex activity, event, and threat detection and image and video forensics continuously aids us in the creation of innovative algorithms and software for automated image and video analysis.

Please reach out to computervision@kitware.com to schedule a discussion with Anthony while he is at this highly respected technical conference.  We look forward to hearing from you and discussing how computer vision and deep learning can solve many challenging problems related to Information Security.

By invitation from the Molecular Sciences Software Institute, Dr. Marcus Hanwell is co-organizing and leading a workshop at Lawrence Berkeley National Laboratory on Nov 30 – Dec 1, 2017. Dr. Hanwell’s workshop will be titled “Quantum Chemistry Schema,” and his co-organizers are Dr. Daniel G. A. Smith of MolSSI, Dr. Bert de Jong of LBNL, and Dr. Aaron Virshup of Autodesk.

From the event page: “The goal of this workshop is to produce a schema that will provide API-like access to pre-existing quantum chemistry packages to enable more complex workflows. … This workshop will pull together a large group of academic and commercial program developers to refine the overall scope and desired aspect of the schema. For further information and current discussion please view the schema’s GitHub page. “

By invitation from the Molecular Sciences Software Institute, Dr. Marcus Hanwell is co-organizing and leading a workshop at Lawrence Berkeley National Laboratory on Nov 30 – Dec 1, 2017. Dr. Hanwell’s workshop will be titled “Quantum Chemistry Schema,” and his co-organizers are Dr. Daniel G. A. Smith of MolSSI, Dr. Bert de Jong of LBNL, and Dr. Aaron Virshup of Autodesk.

From the event page: “The goal of this workshop is to produce a schema that will provide API-like access to pre-existing quantum chemistry packages to enable more complex workflows. … This workshop will pull together a large group of academic and commercial program developers to refine the overall scope and desired aspect of the schema. For further information and current discussion please view the schema’s GitHub page. “

The Machine Learning & Artificial Intelligence (AI) Workshop, sponsored by the United States Geospatial Intelligence Foundation (USGIF), will be held on November 13th in Springfield, VA. Organized by the USGIF Machine Learning and AI Working Group, the workshop will highlight  technical leaders discussing challenges and strategic initiatives focused on AI, machine learning, cognitive computing, and deep learning in geospatial intelligence. 

Image: Person Detection Results Using Deep Learning

Kitware’s Senior Director of Computer Vision, Dr. Anthony Hoogs, has been invited to participate in the panel titled “Hard Problems of Interest” scheduled for 12:45-13:30.  This classified break out session will also include professionals from Riverside Research, National Reconnaissance Office (NRO), Office of the Assistance Secretary of Defense for Research and Engineering (ASD) Department of Defense (DoD), and John Hopkins University Applied Physics Laboratory.  Dr. Hoogs will discuss hard deep learning problems in imagery such as generalizing from few training examples, higher-level reasoning and multi-INT fusion.  Kitware’s Computer Vision Group has significant experience in solving hard problems using deep learning with limited training examples, on satellite, aerial and ground-based imagery for geospatial intelligence.

Please reach out to computervision@kitware.com to schedule a time to meet with Anthony at this timely, unique workshop.  We look forward to seeing you there.

Kitware team members will be at booth 647 during the exhibition, which the conference will hold from November 13 to 16, 2017. Here, the following talks are scheduled. Come to a talk to learn how to get giveaways.

Tuesday, November 14, 2017

• At 11 a.m. MDT, Sébastien Jourdain will present Visualization on the Web with ParaViewWeb & vtk.js
• At 12:30 p.m. MDT, Robert Maynard will review CMake 3.10
• At 2 p.m. MDT, Cory Quammen will highlight What’s New in VTK & ParaView
• At 3:30 p.m. MDT, Alan Scott from Sandia National Laboratories will discuss work with ParaView

Wednesday, November 15, 2017

• At 11 a.m. MDT, Sébastien Jourdain will guide attendees through HPCCloud
• At 12:30 p.m. MDT, Cory Quammen will discuss What’s New in VTK & ParaView
• At 1 p.m., Sébastien Jourdain will review Visualization on the Web with ParaViewWeb and vtk.js
• At 2 p.m. MDT, Ken Moreland from Sandia National Laboratories will present VTK-m: Visualization on Modern Processors
• At 3:30 p.m. MDT, John Patchett from Los Alamos National Laboratory will provide the talk Deepwater Impact Data Set and ParaView

See Kitware team members is these other conference-related activities.

ISAV 2017: In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization

• Kitware participant(s): Patrick O’Leary and Andrew Bauer
• Description: O’Leary is a member of the organizing committee, Bauer is on the programming committee and members of Kitware are co-authors on the papers “In Situ Summarization with VTK-m” and “The ALPINE In Situ Infrastructure: Ascending from the Ashes of Strawman”
• Date(s): Sunday, November 12, 2017
• Time: 9 a.m. to 5:30 p.m. MDT

Intel HPC Developer Conference

• Kitware participant(s): Dave DeMarle
• Description: DeMarle will present “ParaView and VTK w/OSPRay and OpenSWR”
• Date(s): Saturday, November 11, to Sunday, November 12, 2017
• Time: 9 a.m. to 5:30 p.m. MDT

Large Scale Visualization with ParaView

• Kitware participant(s): Dave DeMarle
• Description: DeMarle will co-present the tutorial
• Date(s): Sunday, November 12, 2017
• Time: 8:30 am to 5 p.m. MDT

In Situ Analysis and Visualization with SENSEI

• Kitware participant(s): Andrew Bauer
• Description: Bauer will co-present the tutorial
• Date(s): Monday, November 13, 2017
• Time: 8:30 a.m. to 12 p.m.

On November 2, 2017, Dr. Stephen Aylward will present a seminar as part of VISE’s Fall 2017 series.

Title: Open Science and Computer-Augmented Point-of-Care Ultrasound.

Summary: Open science is a bridge between academia and industry, and it is a way to succeed in academia and industry. The first part of this talk will discuss the challenges and opportunities of open science and how open science can be incorporated into your work, to increase its impact and lead to success. The second part of this talk discusses point-of-care ultrasound. Dr. Aylward’s work in this area is driven by the premise that for the full potential of point-of-care ultrasound to be realized, these systems must be approached as if they were new diagnostic modalities, not simply as inexpensive portable ultrasound imaging systems. These systems must incorporate automated data analysis algorithms, rugged hardware, and specialized interfaces to guide novice users to properly place and manipulate an ultrasound probe and interpret its outputs. Furthermore, the outputs of a point-of-care ultrasound system should be quantitative measures and easy-to-understand reformulations of the acquired data, not b-mode images. It should be assumed that the expertise needed to interpret b-mode images will not be readily available at a point of care, e.g., when used by emergency medical service personnel or military medics to triage trauma patients or when used in schools to screen for scoliosis.

The seminar begins at 12:10 pm at Stevenson Center 5326. For more information, see the VISE Fall 2017 Seminar Series website or contact kitware@kitware.com.

Kitware’s Matt McCormick will be speaking at the PyData Triangle Meetup in Morrisville, NC on Nov 1, 2017. His presentation is titled “Multi-Dimensional, Multi-Modal Image Registration Methods.”

This year’s 2017 Joint Meeting of the Military Sensing Symposium (MSS) Specialty Groups on Battlespace Acoustic, Seismic, Magnetic, and Electric-Field Sensing and Signatures (BAMS) and the National Symposium on Sensor Data & Fusion (NSSDF) will be held October 31 through November 2 in Springfield, VA.  This notable Department of Defense (DoD) conference, sponsored by Army RDECOM ARMDEC, Army RDECOM CERDEC, Army Research Laboratory (ARL), Air Force Research Laboratory (AFRL), Office of Naval Research (ONR), and the Office of the Undersecretary of Defense will be held at the National Geospatial Intelligence Agency (NGA) and will include presentations, poster sessions, and technology specific sessions discussing critical technologies being developed and implemented for the DoD.

Kitware, a Bronze sponsor for this event, will be in attendance and has been selected to provide four technical presentations in the NSSDF meetings on October 31 and November 1.   NSSDF will focus on areas such as cyber situational awareness and situational understanding, methods for improved target tracking, new methods in data fusion, and disruptive technologies.  Kitware’s presentation titled “Fusing Visible and Infrared (IR) Video on Mobile Robots, UAVs and Warfighters for Real-Time, Squad-Level Situational Awareness” will be briefed on October 31 under Session N1D: Fusion.  A Kitware Computer Vision team member will discuss Kitware’s ongoing technology development to improve Intelligence, Surveillance, and Reconnaissance (ISR) capabilities of Army and Marine rifle squads, sponsored by the DARPA Squad-X Core Technologies program. Kitware and its collaborators, the University of Maryland and the University of Pennsylvania, are developing the THreat Reconnaissance and Exploitation from Audio-Video Target eXtraction (THREAT X) system, which focuses on utilizing unmanned systems, and fusing various sensors (Infrared (IR) and RGB) to build automated, intelligence video processing and alert mechanisms supporting the soldier on the ground without added burden.  Kitware has performed multiple data collections over extended periods of time in order to successfully build deep learning computer vision techniques to address person detection and threat classification in battlefield scenarios.  A quantified assessment of this system will be included.  Authors contributing to this project and this paper include Anthony Hoogs, Ph.D., Keith Fieldhouse, and Eran Swears, Ph.D.; all part of Kitware’s Computer Vision Team.

November 1, under Session N2B: Disruptive, Game-Changing Systemic and Technological Concepts, Kitware will brief Deep Learning for Object Detection and Object-based Change Detection in Satellite Imagery.  This presentation will discuss some of Kitware’s technological contributions to the Visual Global Intelligence and Analytics Toolkit (VIGILANT) program, funded by the Air Force.   Kitware is building an open, extensible software framework and demonstration system that will provide cutting-edge automated change detection, tipping, and cueing mechanisms for exploitation of commercial satellite imagery and video.  The system will integrate existing state-of-the-art algorithms from Kitware and the Rochester Institute of Technology (RIT) for satellite image registration, object detection, and object-based change detection incorporating the latest deep learning techniques to enable rapid adaptation to new changes, objects and/or sensor characteristics using the DIRSIG simulation tool.  VIGILANT is built on Kitware-developed open source frameworks for distributed processing and management of heterogeneous big data sources and leverages Kitware’s geographic visualization and analytics capabilities packaged into a modern, browser-based dynamic user interface.  Authors contributing to this project and this paper include Charles Law, Ph.D., Jason Parham, Ph.D., Matt Dawkins, Paul Tunison, David Stoup, Rusty Blue, Ph.D., Keith Feildhouse, Matt Turek, Ph.D., Anthony Hoogs, Ph.D., all from Kitware; S. Han, A. Farafard, J. Kerekes, E. Lentilucci, M. Gartley, A Savakis, T. Rovito, all from RIT; and S. Thomas and C. Stansifer from the Air Force Research Lab (AFRL).

Under Session N2C: Emerging Threats and Challenge Domains, Kitware will present on Automatic Pattern of Life Learning in Satellite Images through Graph Kernels.  This presentation will provide specific details and methods that are successfully being used to learn typical observed patterns in satellite images such as types and density of vehicles at a specific time of day.  Learning patterns can be very challenging due to issues related to different imaging conditions such as resolution, view angle, and sensor type modalities, like Electro-Optical (EO), Infrared (IR), and Hyperspectral Imagery (HSI). To address these, Kitware will brief a new, robust, and scalable approach based on graph modeling and rapid comparison through graph kernels to identify typical patterns in large satellite images. This approach builds upon the contents extracted automatically from the satellite images through deep learning models for object detection and semantic scene segmentation. Authors include John Moeller, Ph.D., Eric Smith, Ph.D., Arslan Basharat, Ph.D., Matt Turek, Ph.D., Anthony Hoogs, Ph.D., all from Kitware, and Erik Blasch from the Air Force Office of Scientific Research (AFOSR).

SegNet deep learning model for semantic segmentation has been extended for satellite images.

Finally, Under Session N2C, Kitware will brief on Using Convolutional Neural Networks (CNNs) for Content-Based Full Motion Video (FMV) Retrieval.  The amount of FMV data available to analysts due to the rapid growth in development and use of Unmanned Aerial Systems (UAS) has dramatically increased.  This poses many problems as automated analytic capabilities have not kept pace and there are very few tools available for alerting or archive search due to challenges related to low resolution, appearance variability, complex scenes, shadows, and other factors.  Deep learning shows great promise in automating the fundamental tasks of FMV, including object recognition, object-based retrieval, and image search.  Kitware will discuss Hierarchical Dynamic Video Exploitation (HiDyVE), which uses CNNs, a form of deep learning for imagery, to detect and describe objects in FMV streams and archives.  The CNNs are used for automatic target recognition when training data per object type is available, and for video search.  This system will be detailed and demonstrated on FMV data in order to show the audience how deep learning improves these capabilities vs. a traditional, non-deep learning approach.  Authors include Matt Dawkins, Roddy Collins, Ph.D., and Anthony Hoogs, Ph.D., all from Kitware’s Computer Vision team.    

Kitware’s Computer Vision group is a leader in building state-of-the-art algorithms and software for automated image and video analytics.  They work extensively with deep learning and computer vision to develop innovative solutions supporting the DoD.  Key focus areas include object detection and tracking, complex activity, event, and threat detection, image and video scene understanding, and image and video forensics.  Kitware’s open source business model and the Computer Vision group’s development of the KitWare Image and Video Exploitation and Retrieval Toolkit permits the DoD Intelligence and Operations communities the opportunity to utilize cutting edge technology bridging the gap between research code, production software, and operational evaluation.  It helps avoid expensive software duplication and redundancy, pushing our partners to accelerate development of newer, better capabilities to deliver to the warfighter sooner.

Please reach out to computervision@kitware.com to set up a discussion with Matt Turek, Keith Fieldhouse, and Rusty Blue during this meeting in order to discuss Kitware’s capabilities and technology contributions to the DoD.

This year’s 2017 Joint Meeting of the Military Sensing Symposium (MSS) Specialty Groups on Battlespace Acoustic, Seismic, Magnetic, and Electric-Field Sensing and Signatures (BAMS) and the National Symposium on Sensor Data & Fusion (NSSDF) will be held October 31 through November 2 in Springfield, VA.  This notable Department of Defense (DoD) conference, sponsored by Army RDECOM ARMDEC, Army RDECOM CERDEC, Army Research Laboratory (ARL), Air Force Research Laboratory (AFRL), Office of Naval Research (ONR), and the Office of the Undersecretary of Defense will be held at the National Geospatial Intelligence Agency (NGA) and will include presentations, poster sessions, and technology specific sessions discussing critical technologies being developed and implemented for the DoD.

Kitware, a Bronze sponsor for this event, will be in attendance and has been selected to provide four technical presentations in the NSSDF meetings on October 31 and November 1.   NSSDF will focus on areas such as cyber situational awareness and situational understanding, methods for improved target tracking, new methods in data fusion, and disruptive technologies.  Kitware’s presentation titled “Fusing Visible and Infrared (IR) Video on Mobile Robots, UAVs and Warfighters for Real-Time, Squad-Level Situational Awareness” will be briefed on October 31 under Session N1D: Fusion.  A Kitware Computer Vision team member will discuss Kitware’s ongoing technology development to improve Intelligence, Surveillance, and Reconnaissance (ISR) capabilities of Army and Marine rifle squads, sponsored by the DARPA Squad-X Core Technologies program. Kitware and its collaborators, the University of Maryland and the University of Pennsylvania, are developing the THreat Reconnaissance and Exploitation from Audio-Video Target eXtraction (THREAT X) system, which focuses on utilizing unmanned systems, and fusing various sensors (Infrared (IR) and RGB) to build automated, intelligence video processing and alert mechanisms supporting the soldier on the ground without added burden.  Kitware has performed multiple data collections over extended periods of time in order to successfully build deep learning computer vision techniques to address person detection and threat classification in battlefield scenarios.  A quantified assessment of this system will be included.  Authors contributing to this project and this paper include Anthony Hoogs, Ph.D., Keith Fieldhouse, and Eran Swears, Ph.D.; all part of Kitware’s Computer Vision Team.

November 1, under Session N2B: Disruptive, Game-Changing Systemic and Technological Concepts, Kitware will brief Deep Learning for Object Detection and Object-based Change Detection in Satellite Imagery.  This presentation will discuss some of Kitware’s technological contributions to the Visual Global Intelligence and Analytics Toolkit (VIGILANT) program, funded by the Air Force.   Kitware is building an open, extensible software framework and demonstration system that will provide cutting-edge automated change detection, tipping, and cueing mechanisms for exploitation of commercial satellite imagery and video.  The system will integrate existing state-of-the-art algorithms from Kitware and the Rochester Institute of Technology (RIT) for satellite image registration, object detection, and object-based change detection incorporating the latest deep learning techniques to enable rapid adaptation to new changes, objects and/or sensor characteristics using the DIRSIG simulation tool.  VIGILANT is built on Kitware-developed open source frameworks for distributed processing and management of heterogeneous big data sources and leverages Kitware’s geographic visualization and analytics capabilities packaged into a modern, browser-based dynamic user interface.  Authors contributing to this project and this paper include Charles Law, Ph.D., Jason Parham, Ph.D., Matt Dawkins, Paul Tunison, David Stoup, Rusty Blue, Ph.D., Keith Feildhouse, Matt Turek, Ph.D., Anthony Hoogs, Ph.D., all from Kitware; S. Han, A. Farafard, J. Kerekes, E. Lentilucci, M. Gartley, A Savakis, T. Rovito, all from RIT; and S. Thomas and C. Stansifer from the Air Force Research Lab (AFRL).

Under Session N2C: Emerging Threats and Challenge Domains, Kitware will present on Automatic Pattern of Life Learning in Satellite Images through Graph Kernels.  This presentation will provide specific details and methods that are successfully being used to learn typical observed patterns in satellite images such as types and density of vehicles at a specific time of day.  Learning patterns can be very challenging due to issues related to different imaging conditions such as resolution, view angle, and sensor type modalities, like Electro-Optical (EO), Infrared (IR), and Hyperspectral Imagery (HSI). To address these, Kitware will brief a new, robust, and scalable approach based on graph modeling and rapid comparison through graph kernels to identify typical patterns in large satellite images. This approach builds upon the contents extracted automatically from the satellite images through deep learning models for object detection and semantic scene segmentation. Authors include John Moeller, Ph.D., Eric Smith, Ph.D., Arslan Basharat, Ph.D., Matt Turek, Ph.D., Anthony Hoogs, Ph.D., all from Kitware, and Erik Blasch from the Air Force Office of Scientific Research (AFOSR).

SegNet deep learning model for semantic segmentation has been extended for satellite images.

Finally, Under Session N2C, Kitware will brief on Using Convolutional Neural Networks (CNNs) for Content-Based Full Motion Video (FMV) Retrieval.  The amount of FMV data available to analysts due to the rapid growth in development and use of Unmanned Aerial Systems (UAS) has dramatically increased.  This poses many problems as automated analytic capabilities have not kept pace and there are very few tools available for alerting or archive search due to challenges related to low resolution, appearance variability, complex scenes, shadows, and other factors.  Deep learning shows great promise in automating the fundamental tasks of FMV, including object recognition, object-based retrieval, and image search.  Kitware will discuss Hierarchical Dynamic Video Exploitation (HiDyVE), which uses CNNs, a form of deep learning for imagery, to detect and describe objects in FMV streams and archives.  The CNNs are used for automatic target recognition when training data per object type is available, and for video search.  This system will be detailed and demonstrated on FMV data in order to show the audience how deep learning improves these capabilities vs. a traditional, non-deep learning approach.  Authors include Matt Dawkins, Roddy Collins, Ph.D., and Anthony Hoogs, Ph.D., all from Kitware’s Computer Vision team.    

Kitware’s Computer Vision group is a leader in building state-of-the-art algorithms and software for automated image and video analytics.  They work extensively with deep learning and computer vision to develop innovative solutions supporting the DoD.  Key focus areas include object detection and tracking, complex activity, event, and threat detection, image and video scene understanding, and image and video forensics.  Kitware’s open source business model and the Computer Vision group’s development of the KitWare Image and Video Exploitation and Retrieval Toolkit permits the DoD Intelligence and Operations communities the opportunity to utilize cutting edge technology bridging the gap between research code, production software, and operational evaluation.  It helps avoid expensive software duplication and redundancy, pushing our partners to accelerate development of newer, better capabilities to deliver to the warfighter sooner.

Please reach out to computervision@kitware.com to set up a discussion with Matt Turek, Keith Fieldhouse, and Rusty Blue during this meeting in order to discuss Kitware’s capabilities and technology contributions to the DoD.

Kitwarean Marcus Hanwell is an invited speaker at the International Workshop and Short Course on the FRONTIERS OF ELECTRON TOMOGRAPHY in the Physical Sciences, happening Oct 23 – 26, 2017 at Lawrence Berkeley National Laboratory in Berkeley, CA. The event brings together leading experts, scientists, postdocs, and students in the field of electron tomography for a 2-day Frontiers Workshop immediately followed by a 2-day short course in electron tomography.

Dr. Hanwell will be conducting a hands-on tutorial for Tomviz, and will also present in the Frontiers Workshop on databases, storage, and visualization.

Kitware is making its presence felt at the International Conference on Computer Vision 2017, happening October 22-29 in Venice, Italy!

Computer vision experts will lead a tutorial on wildlife surveillance, which was selected through a competitive vetting process by the conference organizers. As a Bronze Sponsor, Kitware has a booth in the Expo where representatives from the United States and France offices will be available throughout the conference to discuss Kitware’s vision research and employment opportunities in France and USA.

This is an exciting opportunity to engage with the international vision community to share information on Kitware’s cutting-edge open source vision software, KWIVER, and ongoing research and development in computer vision and machine learning.

Details:

On Sunday, October 22, Anthony Hoogs, the Senior Director of Computer Vision, will provide a tutorial related to Kitware’s current work with the National Oceanographic and Atmospheric Association (NOAA), titled “Open Source Software and Datasets for Wildlife Video Surveillance.” Dr. Hoogs is one of five organizers and speakers showcasing three major wildlife datasets, the existing analytics developed specifically for them, and the open source toolkits implementing those analytics. The importance of environmental monitoring will be front and center with talks on “Underwater Imagery and Video for Fisheries Stock Assessment,” “Underwater Visual Data for Coral Reef Fish Biodiversity Monitoring,” and “Identifying and Re-identifying Individual Animals for the Purpose of Population Assessment.”

Kitware’s Computer Vision group recognizes the potential for computer vision to greatly improve the breadth and depth of environmental monitoring through automating the analysis of images and videos from dedicated sensors, overhead imagery, and even social media. Through a contract with NOAA, Kitware is developing the open-source Video and Image Analytics for Marine Environments (VIAME) toolkit to integrate research developed by the NOAA Fisheries Strategic Initiative on Automated Image Analysis (AIASI)  members and others involved in underwater imagery. Dr. Hoogs is a member of the steering committee for this project.

VIAME is based on KWIVER, the KitWare Video and Image Exploitation and Retrieval toolkit, which is an open source framework for video and image analytics built from Kitware’s years of experience developing analytic systems for various customers in multiple domains. The purpose of VIAME is to integrate efforts across international science centers, universities and businesses as an open-source system for analysis of underwater video and imagery for fisheries stock assessment. It enables the use of existing analytics and rapid, low-cost integration of new algorithms, workflows, and datasets to address unsolved environmental challenges using computer vision. The benefits that vision can provide are extensive and continually evolving.

Join Kitware and its partners for this tutorial to engage with international experts utilizing vision to improve environmental monitoring in terrestrial and marine domains.

Contact:

Please reach out to computervision@kitware.com to schedule meetings throughout this event. Anthony Hoogs and Matt Dawkins from the U.S., and Bastien Jacquet and Pierre Guilbert from the France office will be on-hand for in depth conversations. Find out about Kitware’s computer vision research and capability development supporting academia, defense, environmental monitoring, and commercial domains.

About the event:

ICCV is the premier international computer vision event combining high quality tutorials, workshops, and the main exhibition in order to fuel collaboration amongst students, academics, and industry researchers worldwide. This highly sought after event has limited capacity, according to the ICCV 2017 website, so be sure to register early. The value in attending is exponential as it provides international perspectives on vision techniques, research & development, open-source software, and their current and potential contributions to various domains.

CTO and Kitware co-founder Bill Hoffman will present “Open Source/Open Science Business Model.”

On October 9, 2017, Lucas Gandel, an R&D Engineer at Kitware SAS, will teach T2, a tutorial titled “Developing Virtual Reality applications with the Visualization Toolkit (VTK).”

Kitware is attending, sponsoring, and supporting IEEE Vis in Phoenix Arizona from Oct 1 – Oct 6 2017. Kitware is a silver level sponsor for the event. CEO Lisa Avila is among the Kitwareans planning to attend the conference, and Katie Osterdahl is a publicity team co-chair this year!

Kitwarean Aashish Chaudhary is also participating in The 7th IEEE Symposium on Large Data Analysis and Visualization (LDAV 2017), which will be held in conjunction to the conference.

More details to come about other attendees and presentations.

Distinguished Engineer and Kitware co-founder Charles Law will present “A Web-based, Open-source Data Management Platform Supporting Visualization and Analysis Plugins for Deep Learning in Diagnostic Pathology” from 2:30 to 3 p.m. PST Monday, October 2, 2017.

Kitware co-founder Bill Hoffman will be at All Things Open 2017, which is taking place October 23 – 24 in Raleigh, NC. He’s presenting a talk titled “OPEN SOURCE/OPEN SCIENCE BUSINESS MODEL.”

Bill says, “In this talk I will discuss the successful story of Kitware’s open source business model. Starting with 5 founders, no venture capital, and one really great open source toolkit in 1998, the company has thrived for almost two decades. The slow growth model has resulted in a company of about 150 employees with three US offices and a French office. Our small but dedicated and growing team has had a disproportionate impact on global scientific computing, including the creation of the defacto standard C++ build system CMake. The talk will cover our business model and open source success stories.”

All Things Open is a two-day event that focuses on open source and the open web in the enterprise. The talks and workshops feature a diverse and unique line-up of some of the most well known experts in the world, as well as “new faces you’ll be hearing about for years into the future”. For more information, see their website and sign up for updates.

Kitware’s Senior Director of Computer Vision Dr. Anthony Hoogs has been invited to present at the Big Data & Predictive Analytics Symposium for Intelligence and Defense, happening in Washington, D.C. on September 21-22,  2017. This conference brings together top experts from a community that is ‘shaping the direction of big data and predictive analytics research and development for defense, intelligence, homeland security, and law enforcement’.  To catch his talk, “Research and Development Initiatives in Government” and many others, visit the Big Data event website and register for this exciting conference.

EVENT DETAILS

This year’s conference includes over 20 Guest Experts from Army G8, USN PEO C4I/PMW-120, ONI, DOD OUSD (AT&L), BAE Systems, Booz Allen Hamilton, Basis Technology, Kitware, Inc., and others. Key government and industry experts will lead discussions related to Applying Predictive Analytics to the Defense Mission, Sharing Big Data and Data Science, Deep/Predictive Analytics and Machine Learning, Media Forensics, Cloud Computation, Open Source Software, and much more.

Information sharing and information overload are the major challenges in Big Data and Predictive Analytics today.  Understanding the latest development in technologies, capabilities, and tools to push past these obstacles are of the utmost importance.  Dr. Hoogs will present open-source methods for extracting and indexing content from video archives using deep learning, with examples from the academic community and Kitware’s innovative techniques. His talk is on September 21 from 2:15-2:45 pm.

PRESENTATION SUMMARY

Kitware’s early adoption, integration, and utilization of deep learning techniques has laid the foundation for iteratively improving upon existing technologies. Kitware leverages its expertise in deep learning to innovate powerful applications built on big visual data, GPU computation, and open source software.  Deep learning provides extensive opportunities to improve robustness and accuracy in addressing different customer domains with unique data, requirements, and operational challenges.  Our innovations harness immense computational power and big data to better utilize Convolutional Neural Networks (CNNs) to make sense of images, video, audio, and text files.  We then translate them into relevant information without overtaxing the soldier, analyst, or the end user.    

Dr. Hoogs will discuss how deep learning can address difficult visual problems such as large data volumes, very small training sets, and low resolution source imagery.  Details related to image descriptors, big visual data and challenges, training deep networks, visual-language integration, improved object detection and tracking, media forensics, and open source software will be expanded on as they relate to big data and predictive analytics.  Our ongoing research and development fusing big visual data, deep learning, and open source software will provide the audience with valuable information related to different technologies and end user applications that benefit from this successful fusion and exploitation of “mission-relevant” information.  For instance, we will present on our open source Social Multimedia Query Toolkit (SMQTk), Kitware’s large-scale multimedia analysis tools that automatically understand content from millions of videos and images.  These tools combine our expertise in scene understanding, object detection, event recognition, knowledge discovery and interactive query refinement in order to mine and translate large amounts of data into usable information, quickly.

Kitware’s Computer Vision group recognizes how valuable advancing computer vision and deep learning is in order to greatly improve and push capabilities beyond their limits supporting DoD, Intelligence, Homeland Security, and Law Enforcement communities.  We have worked with various agencies, such as the Defense Advanced Research Project Agency (DARPA), Air Force Research Laboratory (AFRL), and the Intelligence Advanced Research Projects Activity (IARPA).  Kitware has developed and deployed an operational Wide Area Motion Imagery (WAMI) tracking systems for Intelligence, Surveillance, and Reconnaissance (ISR) in theatre, providing analysts with exploitation capabilities that fuse sensors, platforms, and people.  Our work with DARPA on Squad-X has led to extensive research, development, and deployment of robust methods to more accurately identify and track objects and people, delivered straight to the soldier on the ground.  Kitware’s Media Forensics efforts are evolving, permitting Kitware to develop capabilities to detect photo-manipulation in images and video, which will be applied to assess large volumes of data efficiently identifying forged media.  In addition, Kitware is continually improving KitWare Image and Video Exploitation and Retrieval (KWIVER) toolkit, an open source framework for video and image analytics built from Kitware’s years of experience developing analytic systems for various customers in multiple domains.  Please visit our computer vision and KWIVER webpages for more information into our key focus areas and experience.

CONTACT

Please reach out to computervision@kitware.com to schedule meetings throughout this event.  Anthony Hoogs will be on-hand for in depth conversations.  We are looking forward to engaging with this community and sharing information on Kitware’s ongoing research and capability development in computer vision and deep learning as well as our cutting-edge open source vision software, KWIVER.

The 2017 IEEE International Conference on Image Processing (ICIP 2017) is fast approaching, and one of Kitware’s computer vision researchers, Dr. Zhaohui H. Sun, will be in attendance!  This event will be held in Beijing, China, September 17-20. It will “feature world-class speakers, tutorials, and industry sessions to create an excellent forum to foster innovation, entrepreneurship, and networking with academia and industry working in this field.”

Dr. Sun will present three papers in this selective international conference, sharing different techniques and novel methods for image processing.  During his presentation “Reflection Correspondence for Exposing Photograph Manipulation,” he will discuss utilizing image reflections as a strong indicator of content manipulation.  Image reflections are used because they are extremely difficult to fake, since they involve complicated interactions between surface materials, geometry and lighting.  The proposed technique should be able to identify images and video that have been maliciously manipulated. Authors include Eric Wengrowski with Rutgers University, Dr. Sun and Dr. Anthony Hoogs.

Dr. Sun will also present “Compact Image Representation by Binary Component Analysis,“ a method for fractional dimension reduction and face representation. Authors for this paper are Dr. Sun and Dr. Hoogs. The novelty of this paper is an improvement over principal component analysis (PCA) based methods by using binary component analysis (BCA) as an alternative.  Base vectors are restricted to binary values of +1 and -1, resulting in fractional dimension reduction and better face classification performance.

Finally, Dr. Sun will provide the presentation “Reconstruction of Highly Structured Image by Entropy Optimization.”  This presentation will detail an image reconstruction approach that proposes entropy optimization as an alternative to the L0 and L1 optimization that is so widely used in compressive sensing.  Dr. Sun will discuss two reconstruction algorithms based on this approach to address highly structured signals and images with multiple dominant modes.

Kitware’s computer vision team continuously delves into and applies computer vision and deep learning in order to develop and optimize innovative technologies that focuse on image and video processing.  These techniques help to build tools and capabilities to support government and commercial customers, as well as to collaborate with the academic community.  Focus areas such as image and video forensics, complex activity and threat detection, social multimedia analysis, super resolution and 3D vision all benefit from the research and development performed by the computer vision researchers at Kitware.  In addition, the open-source image and video analytics platform, the KitWare Image and Video Exploitation and Retrieval (KWIVER) toolkit, provides the image processing community with an advanced collection of computer vision tools without restrictions.

Please reach out to Dr. Sun at computervision@kitware.com to schedule time to discuss computer vision and deep learning approaches to image processing at ICIP 2017.

Drawings by Andrei State and Sharif Razzaque

About      •      Dates     •    Organizers and Speakers    •    Program    •     Submissions     •     Venue

Presentations from the workshop are available! (link)

The premise of this full-day MICCAI workshop is that for the full potential of point-of-care ultrasound (POCUS) to be realized, POCUS systems must be approached as if they were new diagnostic modalities, not simply as inexpensive, portable ultrasound image systems.

This workshop is dedicated to the research and clinical evaluations of the technologies specific to POCUS. POCUS involves automated data analyses, rugged hardware, and specialized interfaces to guide novice users to properly place and manipulate an ultrasound probe and interpret the returned ultrasound data. In particular, the output of a POCUS system should typically be quantitative measures and easy-to-understand reformulations of the acquired data, not b-mode images; it should be assumed that the expertise needed to interpret b-mode images will not be readily available at the points of care.

Image analysis algorithms as well as tracking and systems engineering are essential to POCUS applications. Example applications include detection of intra-abdominal bleeding by emergency medical services (EMS) personnel for patient triage at the scene of an accident, diagnosis of increased intra-cranial pressure by medics using computer-assisted measurement of optic nerve sheath diameter, and monitoring of liver tissue health in the homes of at-risk patients. At the workshop, attendees will learn from leaders in POCUS research via oral and poster presentations as well as via live demonstrations and a panel discussion.

About

The workshop aims to support and grow the community of POCUS researchers at the Medical Image Computing and Computer Assisted Intervention (MICCAI) conference. Accordingly, the workshop represents a blending of MIC and CAI.

Topics of interest include the following:

• self-contained or easy-to-setup probe tracking systems for in-field use;
• three-dimensional ultrasound reconstruction from imprecisely tracked two-dimensional probes;
• clinical studies of in-field POCUS applications;
• adaption of advanced ultrasound protocols to low-cost probes;
• ultrasound guidance algorithms and interfaces for novice users;
• automated ultrasound image quality assessment;
• tissue characterization in POCUS applications;
• longitudinal registration of POCUS data;
• workflows and interfaces for novice POCUS users, including augmented reality (AR) and virtual reality (VR) displays;
• hardware packaging for rugged, in-field ultrasound applications; and
• simulation strategies for rapid training of EMS personnel and medics for POCUS applications.

The organization of this workshop is supported, in part, by NIH/NIBIB and NIH/NIGMS via 1R01EB021396-01A1: Slicer+PLUS: Point-of-Care Ultrasound

Dates

June 19  –  Submission Deadline (Completed)
July 7  –  Notification of Acceptance (Completed)
July 17  –  Camera-Ready Papers Due, with Confirmed Workshop Registration (Completed)
August 1  –  Final Program Published  (Completed: See below or download PDF)

September 14  –  Full-Day Workshop

Organizers and Speakers

The workshop organizers represent academic, industry, and clinical leaders in the field of POCUS. InnerOptic is a medical device innovator for ultrasound applications. The clinical leaders include an emergency medicine physician, a trauma surgeon, and an orthopedic surgeon from Washington University and Children’s National Medical Center, all of whom are participating in the investigation of POCUS applications. Queens University, Johns Hopkins University (JHU), Brigham and Women’s Hospital (BWH), and Kitware have open-source packages that are being adopted to POCUS applications.  

The workshop organizers are as follows:

• Stephen Aylward, Kitware
• Emad Boctor, JHU
• Gabor Fichtinger, Queens University
• Kevin Cleary, Children’s National Medical Center
• Matt Oetgen, MD, Children’s National Medical Center
• Deborah Kane, MD, Washington University
• Bradley Freeman, MD, Washington University
• Luv Kohli, InnerOptic
• Sonia Pujol, BWH

Final Program (PDF)

Available Presentations

• Invited: Rapid Prototyping of Ultrasound-Guided Intervention Applications
     Gabor Fichtinger, Queen’s University, Canada (PDF)
• Invited: E-FAST and Other In-Field Applications of Computer-Assisted Point-Of-Care Ultrasound
     Stephen Aylward, Kitware, USA (PPTX)
• Combining Automated Image Analysis with Obstetric Sweeps for Prenatal Ultrasound Imaging in Developing Countries
     Thomas L.A. van den Heuvel, Radboud University Medical Center, The Netherlands (PDF)
• Automatic Estimation of the Optic Nerve Sheath Diameter from Ultrasound Images
     Samuel Gerber, Kitware, USA (PPTX)
• A Probe-Camera System for 3D Ultrasound Image Reconstruction
     Koichi Ito, Tohoku University, Japan (PDF)
• Ultrasound Augmentation: Rapid 3-D Scanning for Tracking and On-Body Display
     Hastings Greer, Kitware, USA (PDF)
• Overall Proficiency Assessment in Point-of-Care Ultrasound Interventions: The Stopwatch is not enough
     Matthew Holden, Queen’s University, Canada (PPTX)
• A Novel Ultrasound Imaging Method for 2D Temperature Monitoring of Thermal Ablation
     Chloe Audigier, Johns Hopkins University, Canada (PDF)
• Keynote: Clinical Applications of Point-Of-Care Ultrasound
     Kevin Cleary, Children’s National Health System, USA (PPTX)

Paper Submission, Live Demonstrations, and Paper Publications

Paper Submissions

The organizing committee will judge the papers based on potential impact on patient care, innovation, and methodological soundness.   MICCAI standards regarding conflicts of interest during review, duplicate publications, and scientific/human-subject ethics will be maintained.

Each paper is submitted via email to stephen.aylward@kitware.com and should include the following:

• In the body of the email please provide
  • Title
  • Responsible author, affiliation, and email address
  • Brief description of the associated live demonstration or an indication that there is no associated live demonstration.
  • Preference for oral or poster presentation
• Attached to the email please provide a PDF of the submitted extended abstract / full paper in MICCAI format

Live Demonstrations

Both poster and podium presenters will have the opportunity to provide live demonstrations.  The live demonstrations are anticipated to include not only image analysis demonstrations but also POCUS probes connected to laptops to demonstrate innovations for 1) tissue characterization using gel-based phantoms, 2) embedded tracking systems, and 3) intuitive AR/VR displays.

Publication

Springer has agreed to publish our papers as part of the MICCAI workshop proceedings.  Papers will appear in a volume in Springer’s Lecture Notes in Computer Science (LNCS) series. 

Venue

Hélène Grandmontagne, a business development engineer at Kitware SAS, will present “Kitware’s open source tools for medical imaging” during the Session de présentations de projets, which will take place from 9:45 a.m. to lunch.

Technical Leader Brian Wylie will attend the event.

Stephen Aylward, the MICCAI Society treasurer, will attend the event. He will be part of the Academia & Industry Networking Event on September 11, 2017, at 6 p.m. EST in Centre des congrès room 400A. Those interested in joining Kitware can discuss opportunities at this time.

Kitware team members Dr. Beatriz Paniagua, Dr. Rachel Clipp, Mr. Jeff Webb, and Dr. Stephen Aylward will be attending the Military Health System Research Symposium (MHSRS) 2017 to support our efforts and explore collaborations in physiology modeling, surgical simulation, dental and craniomaxillo facial injury, and traumatic brain injury.

Dr. Clipp will present a paper she has co-authored, titled “On the TBI Initiated Restructuring of Cerebral Microvasculature: A Multi-Fidelity Modeling Approach.”

The MHSRS is an annual Department of Defense scientific symposium that focuses on the medical needs of war fighters. Over 2000 civilian and military attendees  gather to collaborate on topics related to Combat Casualty Care, Military Operational Medicine, Clinical and Rehabilitative Medicine, Medical Simulation and Information Sciences, and Military Infectious Disease. This year’s MHSRS is happening August 27th – 30th at the Gaylord Palms Resort & Convention Center, in Kissimmee FL.

For more information about Kitware’s presence at this symposium, see our blog post:

https://blog.kitware.com/kitware-team-attending-military-health-services-research-symposium/

This year’s International Conference for Free and Open Source Software for Geospatial (FOSS4G) is happening in Boston from August 14 to August 19. FOSS4G is the largest global gathering focused on open source geospatial software, bringing together developers, users, decision-makers and observers from over 40 countries for six days of workshops, presentations, and discussions.

Kitware will be in attendance with two New Technology presentations:

1. “GeoJS: High Performance Geospatial Visualization for Scientific and Infovis Commmunity”, by Aashish Chaudhary, David Manthey, and Jonathan Beezley.

2. “GeoNotebook: an extension to the Jupyter Notebook for exploratory geospatial analysis”, by Christopher Kotfila and Aashish Chaudhary with Rama Nemani of NASA Ames.

Want to know more about GeoJS and GeoNotebook? Start by checking out these blog posts about it: Geospatial visualizations in GeoJS, GeoNotebook: The Architecture, and GeoNotebook: Data-Driven Quality Assurance for Geospatial Data.

Kitware is a sponsor of the event, at which Technical Leader Aashish Chaudhary will co-present “Building Near-Real-Time Processing Pipelines with the Spark-MPI Platform.”

The Federation of Earth Science Information Partners (ESIP) 2017 is taking place in Bloomington, IN from July 25 – 28. The ESIP Federation was founded in 1998 by NASA as a community of researchers and groups that build and interpret applications for Earth and environmental science data. The federation aims to make research data and information more accessible to decision and policy makers, as well as to the public. ESIP’s interdisciplinary and inclusive meetings are a member-led mix of plenary talks, breakout sessions, poster presentations, technical workshops, and networking opportunities about emerging and persistent topics in Earth science data.

Kitware’s Aashish Chaudhary presented a workshop titled “HDF Analytics” on Tuesday, July 25 from 9:30am – 11:00am.
Workshop summary: HDF data from many scientific disciplines can be integrated into analytical tools for analysis and visualization on desktops and over the network. Analytical results can be saved to HDF for archive or distribution.
Remote Participation: Workshop notes folder | Meeting link | Access Code 152-507-869 | Phone (571) 317-3122

For information on Kitware’s high-performance computing and visualization expertise, and how it can be leveraged by your organization, please see contact us at kitware(at)kitware(dot)com or at (518) 371-3971.

From 10:30 to 11:00 a.m. HAST, Kitware co-founder Charles Law will present “Deep learning applied to challenges in detecting melanoma cells in lymph node biopsies.” Read about more activities in which members of Kitware will participate at CVPR.

Computer vision team members Matt Turek and Matt Leotta demonstrate software solutions at a past CVPR exhibition.

This year’s Computer Vision and Pattern Recognition (CVPR 2017) Conference is “the premier annual computer vision event”, drawing thousands of attendees with ties to academia, industry, and the government to Honolulu, Hawaii July 21-26. As a conference organizer, silver sponsor, exhibitor, and selected academic paper presenter, Kitware’s Computer Vision team will be available to discuss and share information on its cutting-edge open source software toolkit, KitWare Image and Video Exploitation and Retrieval (KWIVER), including ongoing research and development (R&D) in deep learning and computer vision.

Two of Kitware’s Computer Vision team leaders have been actively contributing to organizing and planning CVPR 2017. The Senior Director of Computer Vision, Dr. Anthony Hoogs, is a General Chair and responsible for overseeing the Expo, the conference center and the Program Chairs. Of the three GC’s, he is the only one representing a small business. His active participation in CVPR organization over the years has provided a wealth of knowledge and support to the CVPR planning process and has continually pushed computer vision professionals to get involved in CVPR for future growth internationally. Kitware’s Director of Computer Vision, Dr. Matt Turek, serves as a Corporate Relations Chair, greatly benefitting the CVPR Expo through his experience as Corporate Relations Chair for the Winter Conference on Applications of Computer Vision 2016 and many years working with government and industry partners in computer vision.

One of Kitware’s researchers will present a main conference paper presentation titled “Correlational Gaussian Processes for Cross-Domain Visual Recognition,” based on his dissertation research at Stevens Institute of Technology. Lead author and a member of Kitware’s Computer Vision team, Dr. Chengjiang Long will share experimental results of a new probabilistic framework, known as Correlational Gaussian Processes Classifier (CGPC), for joint visual recognition in a collection of images across multiple domains based on co-occurrence statistics of different instances across those domains. This presentation will be on Monday, July 24 in the 10:00-12:00 Poster 3-1 Session, number 19, under Machine Learning, located in the Kamehameha I room.

On July 26th, CVPR will hold a Media Forensics workshop focused on “the role of computer vision and pattern recognition in forensic applications, with special emphasis on media forensics.” Kitware’s Dr. Long will give an oral presentation in Session 4 at 16:30 on “A C3D-based Convolutional Neural Network for Frame Dropping Detection in a Single Video Shot.”  Dr. Long will discuss frame dropping as a type of video manipulation where consecutive frames are deleted to omit content. In the current era of fake news, manipulation of digital images and video is growing dramatically and steps utilizing computer vision and pattern recognition are being explored to mitigate it.  Please check the most recent programs when attending in order to re-confirm date, time, and locations.

During the main conference and exhibition, Kitware’s computer vision team members including Dr. Hoogs, Dr. Turek, Dr. Long, Dr. Matt Leotta, Dr. Arslan Basharat, and Dr. Eran Swears will be available at Kitware’s booth 242 to engage with CVPR participants.  Computer vision and deep learning techniques and capabilities will be shared and demonstrated, such as KWIVER, Kitware’s open-source software toolkit containing an advanced collection of computer vision tools to perform object detection and tracking; activity, event, and threat detection; scene understanding; social multimedia analysis; and 3D reconstruction.

Kitware is actively recruiting for vision researchers and software engineers. In particular, Kitware looks to hire for the following positions: computer vision software developer, computer vision researcher and 3D computer vision researcher. Kitware also looks to add to its list of collaborators. With expertise in social multimedia analysis, object detection, point cloud and depth image processing, event and activity recognition, scene understanding and deep learning, Kitware has worked on a wide range of research and development projects throughout the field of computer vision.

Be sure to reach out to us at computervision@kitware.com to schedule a more detailed conversation during the conference, or just stop by our booth during the Expo. We want to speak with you!

Next week, Jean-Christophe Fillion-Robin will attend the first Western Slicer Project Week held in London, Ontario, Canada. Kitware is proud to be a sponsor and have our tools featured at this event!

Western Project Week Summer 2017

Slicer Project Week is a hands-on activity in which medical image computing researchers and students create solutions using the image computing platform,  3D Slicer, and its CMake , VTK, and ITK components. It is intended for novices as well as experienced users, focusing on learning the basics, developing programs, and interacting with world experts in this exciting field. This is the first extension Slicer project week. Originally proposed as a small Slicer hackfest, it has quickly grown into a full blown project week with an additional meeting in conjunction with SPWW to discuss and develop goals specific to image-guided therapy, making it the inaugural Slicer IGT Project Week as well.

This event is endorsed by the MICCAI Society.

Technical Leader Aashish Chaudhary and Principal Engineer Matt McCormick are chairs of the Birds of a Feather committee. McCormick will attend and will be joined by Principal Engineer Jean-Christophe Fillion-Robin and Francois Budin.

Technical Leader Marcus Hanwell will present “Tomviz: A Platform for Reproducible Materials Tomography” on Thursday, July 13, 2017 from 2 to 2:30 p.m. CT in room 203.

During the 1 to 5 p.m. EST timeframe, Technical Leader Beatriz Paniagua will give the first demo of Slicer Shape AnaLysis Toolbox (SlicerSALT). In addition, Senior R&D Engineer Dženan Zukić will provide a demo with SonoVol.

Principal Engineer Jean-Christophe Fillion-Robin will attend.

Stephen Aylward will attend the event. He is a conference organizer, a member of the program committee, and a venue chair.

Kitware is a sponsor of EIT2017. R&D Engineer Jared Vicory will attend the event to demo software solutions for data analysis and visualization, such as the Visualization Toolkit (VTK) and ParaView.

The event will host Senior Director of Operations-North Carolina Stephen Aywlard as the keynote speaker. He plans to discuss topics such as medical computing, data and analytics, and computer vision at Kitware and to highlight open-source software solutions such as 3D Slicer and the Insight Segmentation and Registration Toolkit.

Julien Jomier and Joachim Pouderoux are organizers of the session “Visualization at Scale: Deployment Case Studies & Experience Report.” The session will highlight ParaView and occur Thursday, June 22, 2017 from 2 to 6 p.m. CEST.

Bill Hoffman will present Building Open Source Global Scientific Computing Infrastructure as a Successful Business on Tuesday, June 13, 2017, during Afternoon Session I. He will also chair Afternoon Session II on the same day.

Joseph Snyder will attend the summit as well. He is coordinating Kitware participation at an exhibition table.

Technical Leader Beatriz Paniagua will teach a workshop on coding on Tuesday, June 13th, 2017.

The United States Geospatial Intelligence Foundation (USGIF) GEOINT 2017 Symposium is fast approaching, and Kitware’s Directors of Computer Vision will be in attendance! This Symposium will take place in San Antonio, TX, at the Henry B. Gonzalez Convention Center June 4-7, 2017. Anthony Hoogs and Matt Turek will be available throughout the entirety of this Symposium to sit down with government representatives and companies interested in Kitware’s advanced capabilities and to show how they translate and add value to geospatial intelligence.

Over the years, Kitware has continuously developed exciting technologies that support the GEOINT community through computer vision and deep learning techniques. These techniques help Kitware build advanced tools and capabilities to support intelligence operations by detecting emerging threats. Complex activity, event, and threat detection capabilities recognize high-value events, behaviors, and activities in cluttered scenes from different types of videos such as Wide Area Motion Imagery (WAMI) and Full Motion Video (FMV).

Kitware’s Social Multimedia Query Toolkit (SMQTK) understands internet video, visualizes and browses large internet video collections, and queries results to enable focused intelligence operations. SMQTK can also incorporate event recognition and scene understanding technologies to offer an integrated approach to analysis.  By adopting and harnessing deep learning techniques tied with computer vision, Kitware has  demonstrated dramatic improvements in technologies focused on hard problems such as extracting meaningful information from low resolution images and video and/or small training sets, and scaling to handle the large data volumes associated with object detection and tracking, event and activity recognition, scene understanding, 3D vision, and image and video forensics.

Contact:

Please reach out to Anthony Hoogs and Matt Turek at computervision@kitware.com to schedule meetings throughout GEOINT 2017.  We look forward to speaking with you about Kitware’s technologies, solutions, and your challenges!

About the event:

GEOINT 2017 is the “nation’s largest gathering of industry, academia, and government to include Defense, Intelligence and Homeland Security Communities as well as commercial, Fed/Civil, State and Local geospatial intelligence stakeholders.” This year’s focus is on advancing capabilities to meet emerging threats and will include over 230 companies, organizations, and academic institutions supporting and showcasing technologies and capabilities to the GEOINT community through education sessions, training, and booth exhibits. Expect the opportunity to network with over 4,000 intelligence professionals and hear insightful keynote speakers such as the Director of the National Geospatial Intelligence Agency (NGA), Director of the Federal Bureau of Investigations (FBI), the Deputy Director of Intelligence Advanced Research Projects Activity (IARPA), and leaders within United States Southern Command (SOUTHCOM) and United States Transportation Command (USTRANSCOM).

Stephen Aylward will provide a podium presentation and a poster presentation, both of which he co-authored with Matt McCormick, Sean Montgomery, Luv Kohli, Jeffrey Lowell, Bradley Freeman, and Deborah Shipley Kane.

Aylward S, Gerber S, McCormick M, Jallais M, Montgomery S, Kohli L, Freeman B, Kane S, “Point-of-care ultrasound for detecting elevated intracranial pressure in the field” SOMSA 2017

Type: Podium presentation

Description from abstract: We have devised a system that will acquire B-mode images using a hand-held, single-crystal ultrasound device (Interson, Inc.) that can transmit images to a tablet or laptop computer over USB. As images are streamed to the computer, the image that best matches a statistical model of the expected appearance of an ideal optical nerve image can be automatically chosen for analysis.

Aylward S, McCormick M, Jallais M, Gerber S, Montgomery S, Kohli L, Freeman B, Kane S, “Computer-Assisted FAST exam for in-field triage” SOMSA 2017

Type: Poster presentation

Description from abstract: Using radiofrequency (RF) data recorded at multiple transmit powers and frequencies from an ultrasound probe (Interson, Inc.) connected via USB to a laptop computer, we applied (1) multi-feature superpixel preprocessing to delineate anatomic regions in those RF data, (2) spectral coherence to detect regions of weak acoustic coupling (e.g., insufficient gel or obscuring ribs), (3) random forest classification to identify regions of interest (e.g., pooled blood), and (4) dynamic texture classification to determine the probe’s general anatomic position.

2017-SOMSA-Aylward-FAST Poster Presentation

Sébastien Jourdain will present Data Analytics with ParaViewWeb and High Performance Data Analytics on DSRC Systems with ParaViewWeb.

Technical Expert Matthew McCormick will offer the workshop “An Overview of Multi-dimensional, Multi-modal, Image Registration Methods and their Application with the Insight Toolkit (ITK) and Tomviz” on May 15, 2017. Technical Leader Marcus Hanwell will attend as well.

At this year’s AUVSI XPONENTIAL conference, Kitware Assistant Director of Computer Vision Keith Fieldhouse will provide a technical presentation, “Linking Unmanned Systems, Visible and IR Video, Computer Vision, and Humans Together for Real-Time, Squad-Level, Battlefield Situational Awareness.” The presentation will take place May 8, 2017, from 4:30 to 5 pm CDT in room C140 of the Kay Bailey Hutchison Convention Center Dallas.

Intelligent integration of platforms, sensors, and software introduces challenges but also permits the exploitation of techniques to enable situational awareness for humans and unmanned systems in dynamic environments. Kitware uses computer vision and deep learning to improve and expand upon existing and future capabilities and techniques for soldiers on the ground. The work described in the presentation seeks to fuse and strategically use the information that these capabilities garner to realize new applications to benefit international government and commercial domains. For more details, please visit the presentation webpage.

According to the conference website, AUVSI XPONENTIAL 2017 is the largest and most comprehensive international trade show that supports robotics and unmanned systems. The event will include “exclusive speakers, innovative programs and dynamic educational opportunities that inspire and strengthen the people who are shaping the future of our industry.” The conference will host over 650 manufacturers, who will exhibit the latest robotics and unmanned technologies. Attendees will include platform developers and providers, integrators, software developers, solution seekers, and researchers, combining an array of specialized and educated professionals all in one arena.

In “ParaView Users – Bring Your Data to GTC, Gather Insights Like Never Before,” NVIDIA’s Chintan Patel discusses a ParaView plug-in, NVIDIA IndeX, which visualizes unstructured, time-series data. He will join Robert Maynard at the GPU Technology Conference to highlight ParaView in the lab “Interactive HPC Volume Visualization in ParaView.”

ParaView will also have a presence in a “Connect with the Experts” session on “HPC Visualization in Virtual Reality.” The session will take place on Tuesday, May 9, 2017, from 9 a.m. to 12 p.m. PST at the Hilton Santa Clara.

In addition, at GTC 2017, Maynard will present “Build Systems: Combining CUDA and Modern CMake.” The presentation will take place on Thursday, May 11, 2017, from 11:30 to 11: 55 a.m. PST in Marriott Salon 3.

Technical Leader Brian Wylie will provide the talk “Bro to Python.”

Assistant Director of Medical Computing Andinet Enquobahrie will speak at the event on open-source virtual systems for surgical planning.