Journal article
Pseudo-Mono for Monocular 3D Object Detection in Autonomous Driving
Abstract
Current monocular 3D object detection algorithms generally suffer from inaccurate depth estimation, which leads to reduction of detection accuracy. The depth error from image-to-image generation for the stereo view is insignificant compared with the gap in single-image generation. Therefore, a novel pseudo-monocular 3D object detection framework is proposed, which is called Pseudo-Mono. Particularly, stereo images are brought into monocular 3D …
Authors
Tao C; Cao J; Wang C; Zhang Z; Gao Z
Journal
IEEE Transactions on Circuits and Systems for Video Technology, Vol. 33, No. 8, pp. 3962–3975
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Publication Date
August 1, 2023
DOI
10.1109/tcsvt.2023.3237579
ISSN
1051-8215