Monday January 29, 2018
Automotive Camera Image Quality I
Session Chairs:
Stuart Perry, University of Technology Sydney (Australia) and Buyue Zhang, Intel Corporation (United States)
8:50 – 10:20 AM
Grand Peninsula Ballroom B-C
This session is jointly sponsored by: Autonomous Vehicles and Machines 2018, and Image Quality and System Performance XV.
8:50AVM-105
Fundamental imaging system analysis for autonomous vehicles, Robin Jenkin, ON Semiconductor (United States)
9:20AVM-106
Optimizing automotive cameras for image quality, Felix Heide and Dave Tokic, Algolux (Canada)
9:40IQSP-107
Color calibration of digital still cameras used on unmanned aerial vehicles, Susan Farnand, Rochester Institute of Technology (United States)
10:00IQSP-108
No reference prediction of quality metrics for H.264 compressed infrared image sequences for UAV applications, Kabir Hossain, Claire Mantel, and Soren Forchhammer, Technical University of Denmark (Denmark)
10:20 – 10:50 AM Coffee Break
Automotive Camera Image Quality II
Session Chairs:
Luke Cui, Amazon (United States) and Darnell Moore, Texas Instruments (United States)
10:50 AM – 12:40 PM
Grand Peninsula Ballroom B-C
This session is jointly sponsored by: Autonomous Vehicles and Machines 2018, and Image Quality and System Performance XV.
10:50AVM-145
P2020 - standard for automotive system image quality, Patrick Denny, Valeo Vision Systems (Ireland)
11:20AVM-146
LED flicker: Root cause, impact and measurement for automotive imaging applications, Brian Deegan, Valeo Vision Systems (Ireland)
11:40AVM-147
Visual quality evaluation of the multi-camera visualization in automotive surround view systems, Vladimir Zlokolica1,2, Mark Griffin1, Aidan Casey1, Daniela Solera1, Brian Deegan1, Patrick Denny1, and Barry Dever1; 1Valeo Vision Systems (Ireland) and 2University of Novi Sad (Serbia)
12:00AVM-148
Detection probabilities: Performance prediction for sensors of autonomous vehicles, Marc Geese, Ulrich Seger, and Alfredo Paolillo, Robert Bosch GmbH - Leonberg (Germany)
12:20AVM-149
Realistic image degradation with a measured PSF, Christian Wittpahl, Hatem Ben Zakour, Matthias Lehmann, and Alexander Braun, Düsseldorf University of Applied Sciences (Germany)
12:40 – 2:00 PM Lunch
2:00 – 3:00 PM PLENARY: Overview of Modern Machine Learning and Deep Neural Networks - Impact on Imaging and the Field of Computer Vision
3:00 – 3:30 PM Coffee Break
Simulation for Autonomous Vehicles and Machines
Session Chairs:
Peter Catrysse, Stanford Univ. (United States); Patrick Denny, Valeo (Ireland); and Darnell Moore, Texas Instruments (United States)
3:30 – 4:50 PM
Grand Peninsula Ballroom B-C
This session is jointly sponsored by: Autonomous Vehicles and Machines 2018, and Photography, Mobile, and Immersive Imaging 2018.
3:30PMII-161
Image systems simulation for automotive intelligence, Henryk Blasinski, Trisha Lian, Joyce Farrell, and Brian Wandell, Stanford University (United States)
3:50AVM-162
Large scale collaborative autonomous vehicle simulation on smartphones, Andras Kemeny1,2, Emmanuel Icart3, and Florent Colombet2; 1Arts et Métiers ParisTech, 2Renault-Nissan, and 3Scale-1 Portal (France)
4:10AVM-163
Assessing the correlation between human driving behaviors and fixation patterns, Mingming Wang and Susan Farnand, Rochester Institute of Technology (United States)
4:30AVM-164
Virtual simulation platforms for automated driving: Key care-abouts and usage model, Prashanth Viswanath, Mihir Mody, Soyeb Nagori, Jason Jones, and Hrushikesh Garud, Texas Instruments India Ltd. (India)
5:00 – 6:00 PM All-Conference Welcome Reception
Tuesday January 30, 2018
7:15 – 8:45 AM Women in Electronic Imaging Breakfast
Keynote: Future with Autonomous Vehicles
Session Chair: Buyue Zhang, Intel Corporation (United States)
9:10 – 10:10 AM
Grand Peninsula Ballroom B-C
AVM-198
Lyft's approach to autonomous vehicles, Luc Vincent, Lyft, Inc. (United States)
Dr. Luc Vincent is vice president of engineering at Lyft, where he leads the company's Marketplace & Autonomous Platform division. His responsibilities include real-time supply and demand matching, real-time pricing, mapping, and also Lyft's "Level 5" group, focused on Self-Driving Technology. Prior to Lyft, he spent 12 years at Google, most recently as Sr Director of Engineering, leading all imagery-related activities of Google's Geo group. His team of engineers, product managers, program managers, and operations experts was responsible for collecting ground-based, aerial, and satellite imagery at global scale and through computer vision, 3D modeling, and deep learning, make it universally accessible and useful to users around the world - from end-users on a mobile phone to geo scientists researching climate change. Dr. Vincent is recognized in particular for having bootstrapped Street View and turned it into an iconic Google product, available in over 80 countries around the globe. He earned his BS from Ecole Polytechnique (France), MS in computer science from University of Paris XI, and PhD in mathematical morphology from Ecole des Mines de Paris. In addition, he was a postdoctoral fellow in the Division of Applied Sciences of Harvard University.
10:00 AM – 7:30 PM Industry Exhibition
10:10 – 10:40 AM Coffee Break
Keynote: Mapping and Localization
Session Chair: Buyue Zhang, Intel Corporation (United States)
10:40 – 11:40 AM
Grand Peninsula Ballroom B-C
AVM-216
Scalable autonomous vehicle mapping and localization on the edge, Sravan Puttagunta, Civil Maps (United States)
Sravan Puttagunta is a co-founder and chief executive officer of Civil Maps, an autonomous vehicle technology company that enables cars to have Cognition through AI, 3D mapping, advanced localization, and crowdsourcing. As CEO, he is executing on a vision for safer, smarter, fully autonomous driving. With his direction, Civil Maps is on track to triple revenue from last year and is providing key technology to several major automakers. He leads the company’s technology teams, who are developing innovative ways for cars to localize in six dimensions (6D) and crowdsource 3D maps at a continental scale. In his previous work, he invented video fingerprinting for linear broadcast TV to track viewing habits and developed software that runs in more than 160 million TVs. He has written substantial portions of artificial intelligence (AI) algorithms for cars which map the world in 3D. Puttagunta holds a master’s in electrical engineering and computer science from the University of California, Berkeley.
Sensor Fusion
Session Chairs:
Umit Batur, Rivian Automotive (United States) and Darnell Moore, Texas Instruments (United States)
11:40 AM – 12:40 PM
Grand Peninsula Ballroom B-C
11:40AVM-256
Multi-sensor fusion for automated driving: Selecting model and optimizing on embedded platform, Shyam Jagannathan, Mihir Mody, Jason Jones, Pramod Swami, and Deepak Poddar, Texas Instruments India Ltd. (India)
12:00AVM-257
Multi-sensor data fusion for vehicle detection in autonomous vehicle applications, Xin Li1, Abu Hasnat Mohammad Rubaiyat1, Yaser Fallah2, and Gaurav Bansal3; 1West Virginia University , 2University of Central Florida, and 3Toyota (United States)
12:20AVM-258
Camera radar fusion for increased reliability in ADAS applications, Ziguo Zhong, Stanley Liu, Manu Mathew, and Aish Dubey, Texas Instruments (United States)
12:40 – 2:00 PM Lunch
2:00 – 3:00 PM PLENARY: Fast, Automated 3D Modeling of Buildings and Other GPS Denied Environments
3:00 – 3:30 PM Coffee Break
Mapping and Localization
Session Chairs:
Umit Batur, Rivian Automotive (United States) and Patrick Denny, Valeo (Ireland)
3:30 – 5:20 PM
Grand Peninsula Ballroom B-C
3:30AVM-280
VOLA large-scale volumetric data for map-building, navigation, autonomy, and machine intelligence at global scale, David Moloney, Movidius (Intel) (Ireland)
4:00AVM-281
Visual SLAM and localization – the hard cases, Catherine Enright and Bassam Abdallah, Valeo Vision Systems (Ireland)
4:20AVM-282
Dense surround view computation with perspective correctness, Christian Fuchs and Dietrich Paulus, University of Koblenz-Landau (Germany)
4:40AVM-283
Vehicle pose estimation from drive recorder images by monocular SLAM and matching with rendered 3D point cloud of surrounding environment, Akiyoshi Kurobe1, Hideo Saito1, and Hisashi Kinoshita2; 1Keio University and 2 DENSO Corporation (Japan)
5:00AVM-284
Loop closure detection in simultaneous localization and mapping using learning based local patch descriptor, Dong-won Shin and Yo-Sung Ho, Gwangju Institute of Science and Technology (Republic of Korea)
5:30 – 7:30 PM EI 2018 Symposium Demonstration Session
Wednesday January 31, 2018
Robotic Vision Techniques for Navigation and Vision I
Session Chairs:
Patrick Denny, Valeo (Ireland) and Darnell Moore, Texas Instruments (United States)
8:50 – 9:50 AM
Grand Peninsula Ballroom B-C
This session is jointly sponsored by: Autonomous Vehicles and Machines 2018, and Intelligent Robotics and Industrial Applications using Computer Vision 2018.
8:50IRIACV-301
Reliable primitive approximation for estimation of robot grasping parameters using 3D-deep neural network, Takuya Torii and Manabu Hashimoto, Chukyo University (Japan)
9:10IRIACV-302
Real-time visual loop closure detection for unmanned aerial vehicles, Semih Karakaya1, Can Erhan1, Evangelos Sariyanidi2, and Hakan Temeltas1; 1Istanbul Teknik Üniversity (Turkey) and 2Queen Mary University of London (United Kingdom)
9:30AVM-303
Semantic image segmentation using Encoder-Decoder Architecture Assisted by Global and Local Attention Models (EDA-GLAM), Hao Xu, Siyang Li, and Chun-Chieh Kuo, Univeristy of Southern California (United States)
10:00 AM – 4:00 PM Industry Exhibit
9:50 – 10:50 AM Coffee Break
Robotic Vision Techniques for Navigation and Vision II
Session Chairs:
Patrick Denny, Valeo (Ireland) and Darnell Moore, Texas Instruments (United States)
10:50 AM – 12:40 PM
Grand Peninsula Ballroom B-C
This session is jointly sponsored by: Autonomous Vehicles and Machines 2018, and Intelligent Robotics and Industrial Applications using Computer Vision 2018.
10:50AVM-345
Pedestrian detection at night using deep neural networks and saliency maps (JIST-first), Duyoung Heo, EunJu Lee, and ByoungChul Ko, Keimyung University (Republic of Korea)
11:10AVM-346
Context aware hyperspectral scene analysis, Christian Winkens and Dietrich Paulus, University of Koblenz-Landau (Germany)
11:30AVM-347
Multiple pedestrian tracking in moving vehicle using online learning of random ferns and feature descriptor of pre-trained shallow convolutional neural networks, SangJun Kim, Jaeyeal Nam, and ByoungChul Ko, Keimyung University (Republic of Korea)
11:50AVM-348
Raindrop detection considering extremal regions and salient features, Vijay C S, Radhesh Bhat, and Vijaya Ragavan, PathPartner Technology Pvt Ltd. (India)
12:10AVM-349
Removing shadows and shading from road surfaces in real time, Bruce Maxwell and Casey Smith, Tandent Vision Science, Inc. (United States)
12:40 – 2:00 PM Lunch
2:00 – 3:00 PM PLENARY: Ubiquitous, Consumer AR Systems to Supplant Smartphones
3:00 – 3:30 PM Coffee Break
System, Imaging, and Vision Architecture
Session Chairs:
Patrick Denny, Valeo (Ireland) and Darnell Moore, Texas Instruments (United States)
3:30 – 4:10 PM
Grand Peninsula Ballroom B-C
3:30AVM-358
Understanding vehicle E/E architecture topologies for automated driving: System partitioning and tradeoff parameters, Mihir Mody, Jason Jones, Kedar Chitnis, Rajat Sagar, Gregory Shurtz, Yashwant Dutt, Manoj Koul, Biju Mg, and Aish Dubey, Texas Instruments India Ltd. (India)
3:50AVM-359
Camera-aware neural architecture for robust automotive vision, Felix Heide and Dave Tokic, Algolux (Canada)
Discussion: Autonomous Vehicles and Machines 2018
Moderators:
Patrick Denny, Valeo (Ireland); Darnell Moore, Texas Instruments (United States); and Buyue Zhang, Intel Corporation (United States)
4:10 – 5:30 PM
Grand Peninsula Ballroom B-C
The conference chairs invite AVM authors and participants to join an interactive session to discuss questions in a moderated open forum.
4:10
Autonomous Vehicles and Machines Authors Q&A
5:00
Open Discussion
5:30 – 7:00 PM EI 2018 Symposium Interactive Papers (Poster) Session
5:30 – 7:00 PM Meet the Future: A Showcase of Student and Young Professionals Research
Thursday February 1, 2018
Keynote: Imaging Sensors and Technologies for Automotive Intelligence
Session Chairs: Arnaud Darmont, APHESA SPRL (Belgium); Joyce Farrell, Stanford University (United States); and Darnell Moore, Texas Instruments (United States)
8:50 – 9:30 AM
Grand Peninsula Ballroom B-C
This session is jointly sponsored by: Autonomous Vehicles and Machines 2018, Image Sensors and Imaging Systems 2018, and Photography, Mobile, and Immersive Imaging 2018.
Dr. Boyd Fowler joined OmniVision in December 2015 as the vice president of marketing and was appointed chief technology officer in July 2017. Dr. Fowler’s research interests include CMOS image sensors, low noise image sensors, noise analysis, data compression, and machine learning and vision. Prior to joining OmniVision, he was co-founder and vice president of engineering at Pixel Devices, where he focused on developing high-performance CMOS image sensors. After Pixel Devices was acquired by Agilent Technologies, Dr. Fowler was responsible for advanced development of commercial CMOS image sensor products. In 2003, Dr. Fowler joined Fairchild Imaging as the CTO and vice president of technology, where he developed SCMOS image sensors for high-performance scientific applications. After Fairchild Imaging was acquired by BAE Systems, Dr. Fowler was appointed the technology director of the CCD/CMOS image sensor business. He has authored numerous technical papers, book chapters, and patents. Dr. Fowler received his MSEE and PhD in electrical engineering from Stanford University (1990 and 1995 respectively).
PMII-415
Advances in automotive image sensors, Boyd Fowler1 and Johannes Solhusvik2; 1OmniVision Technologies (United States) and 2OmniVision Technologies Europe Design Center (Norway)
Imaging Sensors and Technologies for Automotive Intelligence
Session Chairs:
Arnaud Darmont, APHESA SPRL (Belgium); Patrick Denny, Valeo (Ireland); and Joyce Farrell, Stanford University (United States)
9:30 – 9:50 AM
Grand Peninsula Ballroom B-C
This session is jointly sponsored by: Autonomous Vehicles and Machines 2018, Image Sensors and Imaging Systems 2018, and Photography, Mobile, and Immersive Imaging 2018.
9:30IMSE-422
Partial reset HDR image sensor with improved fixed pattern noise performance, Volodymyr Seliuchenko1,2, Sharath Patil1,3, Marcelo Mizuki1, Saad Ahmad1, and Maarten Kuijk2; 1Melexis (Belgium), 2Vrije University Brussel (Belgium), and 3University of Massachusetts Lowell (United States)
Autonomous Vehicles and Machines Open Discussion
Moderators:
Patrick Denny, Valeo (Ireland); Darnell Moore, Texas Instruments (United States); and Buyue Zhang, Intel Corporation (United States)
9:50 – 10:30 AM
Grand Peninsula Ballroom B-C
The conference chairs invite AVM committee members, authors, and conference participants to join an interactive session to discuss various topics in this open forum. Please join us in building the AVM community.