On June 22, the Institute of Electrical and Electronics Engineers (IEEE) International Conference on Computer Vision and Pattern Recognition (CVPR) 2022 announced the best student paper awards, and researchers from Tongji University and Alibaba won the only best student paper award.
This is also the first time that the first author of the award-winning paper has come from a Chinese university since CVPR established the Best Student Paper Award in 2001.
The first author of the paper is Chen Hansheng, a 2020 graduate student from the Institute of Intelligent Vehicles, School of Automotive Engineering, Tongji University and Shanghai Autonomous Intelligent Unmanned System Science Center. His supervisor is Professor Xiong Lu. The corresponding author of the paper is an associate supervisor and assistant to the School of Automotive Engineering, Tongji University. Professor Tian Wei, Alibaba Dr. Wang Pichao.
Accurate pose estimation of objects has always been a difficult problem in the field of autonomous driving.
In this paper, a general probabilistic n-point perspective (PnP) algorithm, EPro-PnP (end-to-end probabilistic PnP), is proposed for the 6-DOF pose estimation problem of objects in monocular images.
EPro-PnP combines the advantages of traditional geometric vision and cutting-edge deep learning fields, and has broad application prospects in robotics, autonomous driving and other fields.
(Reporter Xu Jing made Zhou Jing's video from Tongji University)
Responsible editor: [Sun Jingbo]