Tuesday 19 January 2021
PLENARY: Deep Internal Learning—Deep Learning with Zero Examples
Session Chair: Charles Bouman, Purdue University (United States)
10:00 – 11:10
Plenary Room
Deep internal learning—Deep learning with zero examples
Michal Irani, Professor in the Department of Computer Science and Applied Mathematics at the Weizmann Institute of Science (Israel)
Michal Irani is a professor at the Weizmann Institute of Science. Her research interests include computer vision, AI, and deep learning. Irani's prizes and honors include the Maria Petrou Prize (2016), the Helmholtz “Test of Time Award” (2017), the Landau Prize in AI (2019), and the Rothschild Prize in Mathematics and Computer Science (2020). She also received the ECCV Best Paper Awards (2000 and 2002), and the Marr Prize Honorable Mention (2001 and 2005).
11:10 – 11:40 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
14:30 – 18:00 Break in program to accommodate time zones.
Wednesday 20 January 2021
11:15 – 11:45 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
11:15 – 11:45 Women-in-Engineering Speed Networking (Morning) - take a break from technical sessions to make new connections and greet old friends. Look for the ZOOM link in Discord #announcements.
14:15 – 18:00 Break in program to accommodate time zones.
KEYNOTE: Image Sensors for Automotive Applications
Session Chair: Robin Jenkin, NVIDIA Corporation (United States)
18:00 – 19:15
Blue Room
18:00
Conference Introduction
18:15AVM-130
KEYNOTE: Global shutter image sensors for automotive applications, Boyd Fowler, OmniVision Technologies (United States)
Keynote speaker Boyd Fowler joined OmniVision in December 2015 as the vice president of marketing. Prior to joining OmniVision, he was co-founder and VP of engineering at Pixel Devices, where he focused on developing high-performance CMOS image sensors. After Pixel Devices was acquired by Agilent Technologies, Fowler was responsible for advanced development of commercial CMOS image sensor products. In 2003, he joined Fairchild Imaging as the CTO and VP of technology, where he developed SCMOS image sensors for high-performance scientific applications. After Fairchild Imaging was acquired by BAE Systems, Fowler was appointed technology director of the CCD/CMOS image sensor business. He has authored numerous technical papers, book chapters, and patents. Fowler received his MS and PhD in electrical engineering from Stanford University (1990 and 1995, respectively).
Autonomous Automotive Design
Moderator:
Peter van Beek, Intel Corporation (United States)
Session Chair:
Robin Jenkin, NVIDIA Corporation (United States)
19:45 – 20:45
Blue Room
19:45AVM-113
Single chip auto-valet parking system with TDA4VMID SoC, Mihir Mody1, Kedar Chitnis2, Hemant Hariyani2, Shyam Jagannathan1, Jason Jones2, Gregory Shurtz2, Abhishek Shankar2, Ankur Baranwal1, Mayank Mangla2, Sriramakrishnan Govindarajan1, Aish Dubey2, and Kai Chirca2; 1Texas Instruments India Ltd and 2Texas Instruments (India)
20:05AVM-114
DRAM bandwidth optimal perspective transform engine, Mihir Mody1, Rajasekhar Allu2, Gang Hua2, Brijesh Jadav1, Niraj Nandan2, Ankur Baranwal1, and Mayank Mangla2; 1Texas Instruments India Ltd (India) and 2Texas Instruments Inc (United States)
20:25AVM-115
Data collection through translation network based on end-to-end deep learning for autonomous driving, Zelin Zhang, Waseda Daigaku (Japan)
Thursday 21 January 2021
PLENARY: The Development of Integral Color Image Sensors and Cameras
Session Chair: Jonathan B. Phillips, Google Inc. (United States)
10:00 – 11:10
Plenary Room
The development of integral color image sensors and cameras
Kenneth A. Parulski, Expert Consultant: Mobile Imaging (United States)
Kenneth Parulski is an expert consultant to mobile imaging companies and leads the development of ISO standards for digital photography. He joined Kodak in 1980 after graduating from MIT and retired in 2012 as research fellow and chief scientist in Kodak's digital photography division. His work has been recognized with a Technical Emmy and other major awards. Parulski is a SMPTE fellow and an inventor on more than 225 US patents.
11:10 – 11:40 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
Object Detection & Vision I
Moderator:
Peter van Beek, Intel Corporation (United States)
Session Chair:
Patrick Denny, Valeo Vision Systems (Ireland)
11:40 – 13:00
Green Room
11:40AVM-170
MODETR: Moving object detection with transformers, Ahmad El Sallab and Eslam Bakr, Valeo (Egypt)
12:00AVM-171
GG-Net: Gaze guided network for self-driving cars, Mohamed Hassan1, Muhammad Abbas1, Alaa Osama1, Dalia Anwar1, Mostafa Azzam1, Mohammed Abdelalim Ali1, Hassan Mostafa1, Samah Shafiey1, and Ibrahim Sobh2; 1Cairo University and 2Valeo (Egypt)
12:20AVM-172
Quantitative study of vehicle-pedestrian interactions: Towards pedestrian-adapted lighting communication functions for autonomous vehicles, Guoqin Zang1,2, Shéhérazade Azouigui2, Sébastien Saudrais3, Olivier Peyricot4, and Mathieu Hebert1; 1Université Jean Monnet de Saint Etienne, 2Institut d'Optique Graduate School, 3ESTACA, and 4Cité du Design, Saint-Etienne (France)
12:40AVM-173
End-to-end imaging system optimization for computer vision in driving automation, Korbinian Weikl1,2, Damien Schroeder1, Daniel Blau1,2, Zhenyi Liu3, and Walter Stechele2; 1BMW Group (Germany), 2Technische Universitat Munchen (Germany), and 3Jilin University (China)
14:30 – 18:00 Break in program to accommodate time zones.
Object Detection & Vision II
Session Chair:
Robin Jenkin, NVIDIA Corporation (United States)
19:45 – 20:45
Green Room
19:45AVM-174
Boosting computer vision performance by enhancing the camera ISP, Peter van Beek, Chyuan-Tyng Wu, and Thomas Gardos, Intel Corporation (United States)
20:05AVM-175
Unify the view of camera mesh network to a common coordinate system, Haney Williams and Steven Simske, Colorado State University (United States)
20:25AVM-176
Case study: Optimizing an automotive ISP to maximize object detection accuracy using a HDR sensor, Doug Taylor and Max Leblond, Algolux (United States)
Monday 25 January 2021
PLENARY: Making Invisible Visible
Session Chair: Jonathan B. Phillips, Google Inc. (United States)
10:00 – 11:10
Plenary Room
Making invisible visible
Ramesh Raskar, Associate Professor, MIT Media Lab (United States)
Ramesh Raskar is an associate professor at MIT Media Lab and directs the Camera Culture research group. His focus is on AI and imaging for health and sustainability. They span research in physical (e.g., sensors, health-tech), digital (e.g., automated and privacy-aware machine learning), and global (e.g., geomaps, autonomous mobility) domains. He received the Lemelson Award (2016), ACM SIGGRAPH Achievement Award (2017), DARPA Young Faculty Award (2009), Alfred P. Sloan Research Fellowship (2009), TR100 Award from MIT Technology Review (2004), and Global Indus Technovator Award (2003). He has worked on special research projects at Google [X] and Facebook and co-founded/advised several companies.
11:10 – 11:40 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
Automotive Image Quality I
Moderator:
Peter van Beek, Intel Corporation (United States)
Session Chair:
Patrick Denny, Valeo Vision Systems (Ireland)
11:40 – 13:00
Green Room
11:40AVM-180
Data driven degradation of automotive sensors and effect analysis, Sven Fleck and Benjamin May, obsurver (Germany)
12:00AVM-181
FisheyeDistanceNet++: Self-supervised fisheye distance estimation with self-attention, robust loss function and camera view generalization, Varun Ravi Kumar1,2, Senthil Yogamani3, Stefan Milz2, and Patrick Mäder2; 1Valeo DAR Kronach, 2Technische Universität Ilmenau (Germany), and 3Valeo Vision Systems (Ireland)
12:20AVM-182
About the use of incremental SNR (iSNR) as criteria for the SOTIF of in-vehicle integrated camera sensor (Invited), Christophe Lavergne, Technocentre Renault (France)
Invited speaker Christophe Lavergne is an image sensor and processing expert with Technocentre Renault, France. Lavergne received his PhD (1991) from Paris-Sud University (Paris XI).
12:40AVM-183
An analytic-numerical image flicker study to test novel flicker metrics (Invited), Christian Wittpahl1, Brian Deegan2, Bob Black3, and Alexander Braun1; 1Hochschule Dusseldorf (Germany), 2Valeo Vision Systems (Ireland), and 3Independent (United States)
Invited speaker Christian Wittpahl is a graduate student at the Hochschule (University of Applied Sciences) Düsseldorf, Germany.
Robotic Vision Systems I
Session Chair:
Patrick Denny, Valeo Vision Systems (Ireland)
13:30 – 14:50
Green Room
13:30AVM-208
Replacing LiDAR sensors with low-cost computational sensors, Felix Heide1,2 and Max Leblond1; 1Algolux (Canada) and 2Princeton University (United States)
13:50AVM-209
High precision 3D video streaming for remote autonomous vehicle control, Yi-Hong Liao1, Tyler Bell2, Brian Acosta1, Andrew Bowman1, and Song Zhang1; 1Purdue University and 2University of Iowa (United States)
14:10AVM-210
RoadEdgeNet: Road edge detection system using surround view camera images, Ashok Dahal1, Eric Golab2, Rajender Garlapati1, Varun Ravi Kumar3, and Senthil Yogamani4; 1Valeo DVS Troy, 2University of Michigan (United States), 3Valeo DAR Kronach (Germany), and 4Valeo Vision Systems (Ireland)
14:30AVM-211
Radiometry and photometry for autonomous vehicles and machines - Fundamental performance limits, Robin Jenkin and Cheng Zhao, NVIDIA Corporation (United States)
14:30 – 18:00 Break in program to accommodate time zones.
Automotive Image Quality II
Moderator:
Peter van Beek, Intel Corporation (United States)
Session Chair:
Patrick Denny, Valeo Vision Systems (Ireland)
18:00 – 19:15
Green Room
18:00
Conference Introduction
18:15AVM-184
Update on progress of IEEE P2020 automotive image quality working group (Invited), Margaret Belska, IEEE Standards Association - P2020 Automotive Image Quality Working Group (United States)
Invited speaker Margaret Belska is the chair of the IEEE Standards Association - P2020 Automotive Image Quality Working Group. Belska previously managed the Customer Camera team at NVIDIA, with an objective of ensuring image quality across all segments employing Tegra Mobile Processors, including mobile, automotive, and embedded. Belska has 20 years’ experience in imaging, ranging from space-based scientific cameras to DSLRs and mobile cameras.
18:35AVM-186
Contrast signal to noise ratio, Robin Jenkin, NVIDIA Corporation (United States)
Robotic Vision Systems II
Moderator:
Peter van Beek, Intel Corporation (United States)
Session Chair:
Robin Jenkin, NVIDIA Corporation (United States)
19:45 – 20:45
Green Room
19:45
Conference Introduction
20:05AVM-213
Evaluation of semi-frozen semi-fixed neural network for efficient computer vision inference, Chyuan-Tyng Wu, Peter van Beek, Phillip Schmidt, Joao Peralta Moreira, and Thomas Gardos, Intel Corporation (United States)
20:25AVM-214
Design, implementation, and evaluation of a semi-autonomous, vision-based, modular unmanned ground vehicle prototype, Doncey Albin and Steven Simske, Colorado State University (United States)
Wednesday 27 January 2021
PLENARY: Revealing the Invisible to Machines with Neuromorphic Vision Systems: Technology and Applications Overview
Session Chair: Radka Tezaur, Intel Corporation (United States)
10:00 – 11:10
Plenary Room
Revealing the invisible to machines with neuromorphic vision systems: Technology and applications overview
Luca Verre, CEO and Co-Founder at Prophesee (France)
Luca Verre is co-founder and CEO of Prophesee, the inventor of the world’s most advanced neuromorphic vision systems. Verre is a World Economic Forum technology pioneer. His experience includes project and product management, marketing, and business development roles at Schneider Electric. Prior to Schneider Electric, Verre worked as a research assistant in photonics at the Imperial College of London. Verre holds a MSc in physics, electronic and industrial engineering from Politecnico di Milano and Ecole Centrale and an MBA from Institut Européen d'Administration des Affaires, INSEAD.
11:10 – 11:40 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
13:00 – 13:30 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
14:30 – 18:00 Break in program to accommodate time zones.
19:15 – 19:45 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
19:15 – 19:45 Women-in-Engineering Speed Networking (Evening) - take a break from technical sessions to make new connections and greet old friends. Look for the ZOOM link in Discord #announcements.