2019.12.18 Jenq-Neng Hwang:Coordinated 3D World Exploration of Big Visual Data for Smart City and Autonomous Driving Applications

讲座题目:Coordinated 3D World Exploration of Big Visual Data for Smart City and Autonomous Driving Applications

主讲人:Prof. Jenq-Neng Hwang


开始时间:2019-12-18   13:00:00





Dr. Jenq-Neng Hwang received the BS and MS   degrees, both in electrical engineering from the National Taiwan University,   Taipei, Taiwan, in 1981 and 1983 separately. He then received his Ph.D.   degree from the University of Southern California. In the summer of 1989, Dr. Hwang joined the Department of Electrical and Computer Engineering (ECE) of  the University of Washington in Seattle, where he has been promoted to Full   Professor since 1999. He served as the Associate Chair for Research from 2003   to 2005, and from 2011-2015. He is currently the Associate Chair for Global   Affairs and International Development in the ECE Department. He is the   founder and co-director of the Information Processing Lab., which has won   CVPR AI City Challenges awards consecutively in the past years. He has  written more than 350 journal, conference papers and book chapters in the   areas of machine learning, multimedia signal processing, and multimedia   system integration and networking, including an authored textbook on   Multimedia Networking: from Theory to Practice, published by   Cambridge University Press. Dr. Hwang has close working relationship with the   industry on multimedia signal processing and multimedia networking.

Dr. Hwang received the 1995 IEEE Signal   Processing Society's Best Journal Paper Award. He is a founding member of   Multimedia Signal Processing Technical Committee of IEEE Signal Processing   Society and was the Society's representative to IEEE Neural Network Council   from 1996 to 2000. He is currently a member of Multimedia Technical Committee  (MMTC) of IEEE Communication Society and also a member of Multimedia Signal  Processing Technical Committee (MMSP TC) of IEEE Signal Processing Society.   He served as associate editors for IEEE T-SP, T-NN and T-CSVT, T-IP and   Signal Processing Magazine (SPM). He is currently on the editorial board of   ZTE Communications, ETRI, IJDMB and JSPS journals. He served as the Program Co-Chair   of IEEE ICME 2016 and was the Program Co-Chairs of ICASSP 1998 and ISCAS   2009. Dr. Hwang is a fellow of IEEE since 2001.



With the huge amount of networked static   surveillance and moving video cameras available everywhere nowadays, such as   the cameras on the vehicles/drone for autonomous driving or aerial   surveillance applications, there is an urgent need of systematic and   coordinated mining of the detected video objects in the 3D physical world, so   that the explored information can be exploited for various smart city   applications. To achieve this goal, several critical challenges need to be   effectively overcome, more specifically, reliable SLAM-based visual odometry   for pose estimation (self-calibration) of moving cameras, robust   tracking-by-detection and detection-by-tracking for detected object   associations in presence of missing or erroneous detections, reliable ground   plane estimation for 2D to 3D inferences, finally efficient 3D pose   estimation for action description of detected human. In this talk, I will   cover all these topics and propose our optimized strategies of integrating   these research components, practical applications for smart city and   autonomous driving will be demonstrated.