The Fifth Annual Workshop on Naval Applications of Machine Learning is the premier annual event showcasing current machine learning research relevant to Naval applications. NAML 2021 is focusing on the dynamics, obstacles, and successes of transitioning machine learning and AI research and preparing these technologies for real-world applications.

Kitware is looking forward to being involved in NAML 2021. We will be giving the following tutorial session. Anyone involved in the defense industry can register to attend here.

___________________________________________________________________________________________________________________________

VIAME – An Open Source Video Analytics Toolkit for the Maritime Environment

Wednesday, March 24 at 3:30 pm ET

Tutorial Presented by Matt Dawkins, senior R&D engineer at Kitware*

In cooperation with the National Oceanic and Atmospheric Administration’s (NOAA) Automated Image Analysis Strategic Initiative, Kitware and its partners have developed Video and Image Analytics for Marine Environments (VIAME). VIAME is an open source computer vision software platform designed for do-it-yourself artificial intelligence. It is an evolving toolkit that contains many workflows used to generate different object detectors, full-frame classifiers, image mosaics, rapid model generation, image and video search, and methods for stereo measurement.

Originally targeting marine species analytics, it now contains many common algorithms and libraries and is also useful as a generic computer vision library outside of underwater images and videos. VIAME is available as a desktop or a web application.

*This tutorial is pre-recorded, but there will be a live Q&A session with Matt. 

Kitware is proud to be a Silver sponsor of the 2021 Winter Conference on Applications of Computer Vision (WACV). This conference is being held virtually from Tuesday, January 5 through Saturday, January 9.

WACV is known as the Institute of Electrical and Electronics Engineers (IEEE) and the Technical Committee on Pattern Analysis and Machine Intelligence’s (PAMI-TC) premier meeting on applications of computer vision. This conference promotes collaboration, research and development, and insight into computer vision applications and technology through workshops, tutorials, and main sessions. The event provides in-depth information on cutting edge research advances in applications of computer vision technology. WACV attendees include academia, industry, and government representatives. 

We are happy to be supporting this community as we continue to collaborate and engage through virtual channels. We also hope to recruit talented computer vision professionals to join our team here at Kitware.

This year, we will be presenting a paper at the main conference in addition to a workshop. 

Workshop: Third International Workshop on Human Activity Detection in Multi-camera, Continuous, Long-duration Video

Tuesday, January 5, 2021, from 11 am – 3:15 pm ET (Virtual)

When humans interact with machines and other agents, advanced pattern recognition techniques are predominately used to interpret the complex behavioral patterns. Computer vision is key to the analysis and synthesis of human behavior. Still, it stands to gain much from multimodality and multi-source processing to improve accuracy, resource use, robustness, and contextualization.

This workshop is for researchers looking to model human behavior under its multiple facets, with particular attention to multi-source aspects, including multi-sensor, multi-participant, and multimodal settings. The diversity of human behavior, the richness of multi-modal data that arises from its analysis, and the multitude of applications that demand rapid progress in this area make this workshop a timely and relevant discussion and dissemination platform.

This workshop was organized by Afzal Godil, Jonathan Fiscus, Yooyoung Lee, Anthony Hoogs, and Reuven Meth.

Paper Presentation: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection

Wednesday, January 6, 2021, between 9:45 – 11 pm ET Time Slot (Virtual)

Authors

Kellie Corona, Katie Osterdahl, Roddy Collins, Anthony Hoogs

Abstract

We present MEVA, a new and very-large-scale dataset for human activity recognition. Existing surveillance datasets either focus on activity counts by aggregating public video disseminated due to its content, which typically excludes same-scene background video, or they achieve persistence by observing public areas and thus cannot control for activity content. Our dataset is over 9300 hours of untrimmed, continuous video, scripted to include diverse, simultaneous activities, along with spontaneous background activity. We have annotated 144 hours for 37 activity types, marking bounding boxes of actors and props.

Our collection observed approximately 100 actors performing scripted scenarios and spontaneous background activity over a three-week period at an access-controlled venue, collecting in multiple modalities with overlapping and non-overlapping indoor and outdoor viewpoints. The resulting data includes video from 38 RGB and thermal IR cameras, 42 hours of UAV footage, as well as GPS locations for the actors. 122 hours of annotation are sequestered in support of the NIST Activity in Extended Video (ActEV) challenge; the other 22 hours are available on our website, along with 328 hours of ground camera data, 4.6 hours of UAV data, and 9.6 hours of GPS logs.

Additional derived data includes camera models geo-registering the outdoor cameras and a dense 3D point cloud model of the outdoor scene. The data was collected with IRB oversight and approval and released under a CC-BY-4.0 license.

Kitware is happy to be participating in the 34th National Alliance for Medical Image Computing (NA-MIC) Project Week. Since 2005, this event has increased the impact of medical image computing through community-based open-access hackathons. NA-MIC Project Week predominately focuses on 3D Slicer, an open source visualization and medical image analysis application, and other related tools and projects.

Kitware Presentations Overview

Monday, December 14

SlicerSALT: Shape Analysis
Presenter: Beatriz Paniagua, Assistant Director of Medical Computing, Kitware

SlicerHeart
Presenter: Andras Lasso

SlicerCMF: Craniofacial image processing
Presenter: David Allemang, R&D Engineer, Kitware

MONAI
Presenter: Stephen Aylward, Senior Director of Strategic Initiatives, Kitware

aevaSlicer volumetric mesh generation from segmentations
Presenter: Samantha Horvath, Senior R&D Engineer, Kitware

LookingGlass: Slicer and VTK integration with LookingGlass Holographic Display
Presenters: Stephen Aylward, Senior Director of Strategic Initiatives, Kitware; Jean-Christophe Fillion-Robin, Principal Engineer, Kitware

Tuesday, December 15

New Features in 3D Slicer; Focus on End to End Solutions

Moderators: Andas Lasso; Beatriz Paniagua, Assistant Director of Medical Computing, Kitware; Jean-Christophe Fillion-Robin, Principal Engineer, Kitware; Samantha Horvath, Senior R&D Engineer, Kitware; Steve Pieper

Wednesday, December 16

Live Discourse – Questions and Answers from Users and Developers

One-hour presentation on MONAI

Presenters: Stephen Aylward, Senior Director of Strategic Initiatives, Kitware; Matthew McCormick, Principal Engineer, Kitware

Thursday, December 17

 itk.js, vtk.js, ParaView medical, and web assembly

Presenters: Matthew McCormick, Principal Engineer, Kitware; Forrest Li, R&D Engineer, Kitware

Registration

If you haven’t signed up yet, registration is free! Click here to get started.

The IEEE Workshop on Information Forensics and Security (WIFS) will be held virtually from Sunday, December 6 – Friday, December 11. This event brings researchers together to discuss emerging challenges, exchange fresh ideas, and share their state-of-the-art results and technical expertise in the areas of information security and forensics.

This year, the theme of WIFS 2020 is “Living in Synthetic Reality.” Participants will explore the impact of synthetic content generation on information integrity and encourage discussion and awareness of its effects on society. Attendees will enjoy special sessions, keynote speakers, and hands-on tutorials. 

Anthony Hoogs, senior director of computer vision, is serving as the general co-chair for this workshop. As the leader of Kitware’s Computer Vision Team, he is dedicated to advancing research and technology development to better understand and utilize artificial intelligence. Please visit our computer vision webpage for more information about our key focus areas and experience.

Session 1: Monday, November 30 from 8:00 am – Noon EST

Session 2: Monday, November 30 from 1:00 pm – 5:00 pm EST

The “Modern Insights from Microscopy Images: An Introduction to Web-based Methodologies” tutorial is part of the From Images to Knowledge with ImageJ & Friends Virtual Conference (I2K 2020).

Abstract: Technological evolution poises modern, web-based methods as the future of bioimage analysis. Moreover, web-based methods are better suited to solve challenges such as extremely large images and reproducibility. In this tutorial, we will introduce the concepts, approaches, and tools for modern, web-based open source bioimage analysis. An introduction to the fundamentals of web-based imaging is covered through the topics of web-based image visualization, image data storage for the web, distributed image processing in the cloud, asynchronous programming, and re-usable deep learning components on the web. Content will be presented in Jupyter notebook modules consisting of oral presentations, interactive material, and hands-on exercises.

To participate, students are required to have a laptop or a workstation, Chrome web browser, and a GitHub account. Students should also install miniconda or anaconda to obtain the conda package manager.

This tutorial is being taught by Matthew McCormick, a principal engineer on Kitware’s Medical Computing Team.

Kitware has been a long-standing participant in the International Conference for High-Performance Computing, Networking, Storage, and Analysis (SC20). As Supercomputing goes virtual this year, we remain committed to this community and plan to stay connected “everywhere you are.” 

ISAV 2020: In Situ Infrastructures for Enabling Extreme-scale Analysis and Visualization

pyHPC 2020: 9th Workshop on Python for High-Performance and Scientific Computing

Friday, November 13 from 10:00 AM- 5:40 PM PM EST (Virtual)

Python remains one of the fastest-growing programming languages with large communities of users in academia and industry. Its high-level syntax lowers the barrier to entry and improves productivity, making it the “go-to” language for data science and machine learning. It also remains increasingly popular in high performance and distributed computing.

PyHPC returns to Supercomputing to connect researchers, developers, and Python practitioners to share their experiences using Python across a broad spectrum of disciplines and applications. The goal of the workshop is to provide a platform for the community to present novel Python applications from a wide range of disciplines, to enable topical discussions regarding the use of Python, and to share experiences using Python in scientific computing and education.

This workshop aims to help address the needs of the HPC community and to help shape future directions in high performance and scientific computing.

Kitware is proud to continue its support of the IEEE Vis community as a sponsor of the VIS 2020 conference. The conference, which takes place October 25-30, will be fully virtual this year due to COVID-19.

The event is known as the premier forum for advances in theory, methods, and applications of visualization and visual analytics. It brings together an international community of researchers and practitioners from universities, government, and industry to exchange recent findings on the design and use of visualization tools.

Kitware is excited to be presenting at the conference virtually this year. Please see below for more details.

ParaView Tutorial

JupyterCon brings together Project Jupyter platform users for in-depth training, insightful keynotes, and practical talks. This year, the online conference will include mini-events, learning opportunities, and collaboration with other attendees. Having a special connection with the Jupyter community, Kitware is excited to be giving two talks at JupyterCon this year. Please see below for more details.

Pulse Physiology Engine: An Interactive Human Physiology Simulator

Kitware is pleased to share Matthew Dawkins has been invited to present a plenary talk at the MASTS Annual Science Meeting 2020. 

Matthew’s presentation takes place Tuesday, October 6 from 12-12:30 PM ET. He will give an overview of the Video and Image Analytics for Marine Environments (VIAME), an open source do-it-yourself AI platform that enables marine scientists to leverage deep learning for image and video analysis without any knowledge of AI, deep learning, or programming.

The Marine Alliance for Science and Technology for Scotland (MASTS) is a consortium of organizations engaged in Marine Science. The MASTS Annual Science Meeting is the UK’s largest marine science conference. This year, the conference will take place virtually, giving everyone around the world access from their home.

Attendees of the conference will have a chance to look back at the significant progress made by MASTS partners and collaborators, and look forward to 2021, which sees the start of the decade of ocean science for sustainable development. The conference will examine the modern challenges that face our marine waters, and identify ways and means to conserve and sustainably use the oceans, seas and marine resources for sustainable development.

For more details and to register, visit the conference registration page.

October 4: Advances in Simplifying Medical Ultrasound (ASMUS) Workshop

October 4: The Shape in Medical Imaging (ShapeMI) Workshop

The goal of this workshop is to present the leading methods and applications for advanced shape analysis and geometric learning in medical imaging. It will provide a venue for researchers working in shape/geometric modeling, learning, analysis, statistics, classification and applications to share novel ideas, to present recent research results, and to interact with each other.

The topics that will be discussed at the Shape in Medical Imaging Workshop include:

• Shape Processing and Analysis
• Shape Learning and Classification
• Geometric Learning and Manifold-based Methods
• Statistics of Shapes and Deformations
• Spectral Shape Analysis
• Spectral Clustering and Dimensionality Reduction
• Shape Modeling and Representation
• Shape Segmentation, Registration, and Correspondence
• Longitudinal Shape Analysis and Processing
• Medical Applications focused on Shape Analysis
• Evaluation/quality assessment of shape models
• Relevant demos of freely available shape analysis software

This workshop is co-organized by Dr. Beatriz Paniagua, assistant director of medical computing at Kitware.

Kitware is proud to be involved in the 2nd NOAA Workshop on Leveraging AI in Environmental Sciences. 

On Tuesday, September 22, from noon to 2 PM ET, Matthew Dawkins,  Anthony Hoogs, and Aashish Chaudhary will present a tutorial on the Video and Image Analytics for Marine Environments (VIAME) toolkit, a do-it-yourself AI platform that enables marine scientists to leverage deep learning for image/video analysis without any knowledge of AI, deep learning or programming.

According to NOAA, the goal of the workshop is to help gather scientists, program managers, and leaders from the public, academic, and private sectors and enable them to meet and exchange experiences related to the development and adaptation of AI tools and applications. This year’s workshop will be hosted virtually and span over several months.

Full details about Kitware’s involvement in the workshop can be found in this blog post.

Kitware is proud to be involved in the 2nd NOAA Workshop on Leveraging AI in Environmental Sciences.

On Thursday, August 27, at 1 PM ET, Matthew Dawkins from our Computer Vision Team will provide a 20-minute overview of the Video and Image Analytics for Marine Environments (VIAME) toolkit, a do-it-yourself AI platform that enables marine scientists to leverage deep learning for image/video analysis without any knowledge of AI, deep learning or programming.

According to NOAA, the goal of the workshop is to help gather scientists, program managers, and leaders from the public, academic, and private sectors and enable them to meet and exchange experiences related to the development and adaptation of AI tools and applications. This year’s workshop will be hosted virtually and span over several months.

As part of this same workshop, Kitware will also conduct a two-hour tutorial on VIAME, scheduled for September 22.

Full details can be found in this blog post.

Kitware is proud to have the following paper accepted at the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) held in conjunction with the 43rd Annual Conference of the Canadian Medical and Biological Engineering Society:

“Parameterization of Respiratory Physiology and Pathophysiology for Real-Time Simulation”

Authors: Jeffrey Webb, Aaron Bray, Rachel Clipp

This paper outlines the recent enhancements to Kitware’s Pulse Physiology Engine respiratory software that has resulted in improved simulation functionality and results. Some of these improvements include:

• The ability to apply realistic patient variability using discretized lumped-parameters that define lung volumes, compliances, and resistances.
• A new sigmoid compliance waveform to help meet the validation of compartment pressures, flows, volumes, and substance values.
• Further parameterization and enhanced logic for the application of pathophysiology to allow for more accurate modeling of both restrictive and obstructive diseases for mild, moderate, and severe cases.

The paper presentation is scheduled for Monday, July 20 from 13:30-17:30 EDT. Sessions will be available to conference attendees on-demand through August 24. For more information and to watch the session, please visit the EMBC website.

Kitware is pleased to have our training session proposal accepted for GEOINT 2020! Though GEOINT was canceled due to COVID-19, the USGIF extended us an invitation to conduct our training virtually as part of the GEOConnect Series Training.

Titled, “3D Reconstruction from Overhead Imagery using Open Source Software,” this training session is for anyone with an interest in learning more about how 3D models are built from aerial imagery and video. Some of the topics covered include:

• An overview of 3D reconstruction algorithms – learn the terminology and gain high-level understanding of how 3D reconstruction pipelines work.
• Data collection – guidance on how (and how not) to collect imagery to obtain the best results.
• Survey of software – learn what 3D reconstruction software is available with an emphasis on open source software.
• Demo of TeleSculptor – learn some of the features of Kitware’s open source TeleSculptor software for 3D reconstruction from FMV.   

Registration for the training session is now open!

CVPR is the premier annual computer vision conference in the world and it’s where you will find the largest gathering of computer vision, machine learning, and artificial intelligence professionals. Kitware’s computer vision team has had a long-term commitment to CVPR and although this year’s event will be a virtual conference due to COVID-19, we look forward to staying engaged and interacting with this community.

Kitware is actively participating in CVPR 2020 and is proud to have a paper accepted at this highly selective conference. In addition, we are helping to organize the full day workshop on media forensics and are sponsoring the EarthVision workshop. Finally, our senior director of computer vision served as an area chair to assist with the main conference paper selection. The event details are listed below. For more information regarding our involvement at CVPR 2020 and our deep-rooted connection to this community, visit our blog. 

DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-move Forgery Detection and Localization

Manipulated images are being used for nefarious purposes to hide content or to duplicate certain objects through copy-move operations. Well-crafted forgery in images can be very challenging for both a human or a machine to discover (e.g. When an image patch with a uniform background is copied to hide an object). In this paper, we propose a Generative Adversarial Network with a dual-order attention model to detect and localize copy-move forgery. You can read the full paper here. 

Paper Presentation with Live Q&A: Tuesday, June 16, 2020, from 4-6 PM and Wednesday, June 17, 2020 4-6 AM PT

Authors: Ashraful Islam, Chengjiang Long, Arslan Basharat, and Anthony Hoogs

EarthVision: Large Scale Computer Vision for Remote Sensing Imagery

Computer vision, machine learning, and signal/image processing are all critical components to Earth observation and remote sensing. Together, they provide large-scale, homogeneous information about processes occurring at the surface of the Earth that can have a big impact on human society, economy, industry, and the planet. This workshop aims to raise awareness of this highly challenging and quickly evolving field of research and to foster collaboration between the computer vision and Earth observation communities. Click for more information about the workshop. 

Date: Sunday, June 14, 2020 (full day)

Workshop on Media Forensics

Media forensics has recently become a topic of interest within the computer vision community as a result of the increasing prevalence of fabricated media spreading misinformation. And now, with the emergence of more sophisticated ML and CV techniques, media forensics has become a broad and prominent area of research. That’s why it is critical to keep advancing on all fronts of media forensics, from the detection of manipulations to biometric implications, misrepresentation/spoofing, and more. Click for more information about the workshop.

Date: Monday, June 15, 2020 (full day)

Kitware Co-organizers: Arslan Basharat, assistant director of computer vision; Scott McCloskey, assistant director of computer vision

To learn more about Kitware’s computer vision work, please reach out to computervision@kitware.com. We look forward to engaging with this community and sharing information about Kitware’s ongoing research and capability development in computer vision and deep learning, as well as our cutting-edge open source software.