GPU Technology Conference

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 andExplore 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.