报告题目：From SLAM to Tracking and 3D Localization of Detected Objects
报告人：黄正能教授
报告时间：12月13日 9:30
报告地点：行政楼912
报告人简介:
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 several AI City Challenges awards in the past years. He has written more than 330 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.
报告内容简介:
There are more and more visual data collected from the constantly moving cameras on the vehicles or drones. Built upon the success of various deep learning architectures for image-based object detection, segmentation and 2D pose estimation, there is an urgent need of systematic and coordinated mining of the dynamic environment in the 3D physical world, so that the explored information can be exploited for various smart city applications, such as intelligent transportation, autonomous driving, aerial surveillance, etc. To accomplish this, we need all the moving monocular cameras to be able to reliably track by detection,3D localize and pose estimate the detected moving objects (such as humans and cars) in a unified world coordinate system, so that all the analyzed information can be easily coordinated and exchanged. In this talk, I will first talk about the techniques of improving the object detectors’ performance based on tracking. Then describe the visual odometry techniques to self-localize the moving cameras on the cars and drones, followed by the ground plane estimation to allow the detected moving objects to be localized in the 3D space. Finally, for those 3D tracked humans, whose 3D poses can also be estimated for action and behavior analysis purposes.
