讲座内容：Joint Monocular Vehicle 3D (JMV3D) for Localization, Tracking and Segmentation
讲座人：黄正能教授
讲座时间：11月29日 9:30-11:00
腾讯会议：892 2625 8886
Abstract：
Sensing and perception systems for autonomous driving vehicles in road scenes are composed of four crucial components: object detection, tracking, segmentation, and 3D localization. While all these components are inherently intertwined, most relevant papers tend to only focus on a subset of these components. We propose a joint monocular vehicle 3D (JMV3D) based framework that effectively tracks detected moving objects over time and estimate their 3D localization information as well as segmentation masks from a sequence of 2D images captured from a dash camera on a moving vehicle. Our system contains an RCNN-based Localization for Tracking Network, which works in concert with fitness evaluation score (FES) based single-frame optimization to get more accurate and refined 3D vehicle localization. The object association leverages deep pairwise contrastive learning to identify objects in various poses and viewpoints with appearance cues. A straightforward combination of a 3D Kalman filter and the Hungarian algorithm is further utilized for robust instance association via both feature similarity and 3D localization information. Our proposed JMV3D pipeline ranks 1st place on the KITTI-MOTS leaderboard, both in BMTT Challenges in CVPR 2020 and ICCV 2021, and also achieves impressive results among all image-based solutions on nuScenes 3D detection and tracking benchmark.
Short Bio：
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 is the Director of the Information Processing Lab. (IPL), which has won several AI City Challenges and BMTT Tracking awards in the past years. Dr. Hwang served as associate editors for IEEE T-SP, T-NN and T-CSVT, T-IP and Signal Processing Magazine (SPM). He was the General Co-Chair of 2021 IEEE World AI IoT Congress, as well as the program Co-Chairs of IEEE ICME 2016, ICASSP 1998 and ISCAS 2009. Dr. Hwang is a fellow of IEEE since 2001.
