The Library
ESGN : efficient stereo geometry network for fast 3D object detection
Tools
Gao, Aqi, Pang, Yanwei, Nie, Jing, Shao, Zhuang, Cao, Jiale, Guo, Yishun and Li, Xuelong (2024) ESGN : efficient stereo geometry network for fast 3D object detection. IEEE Transactions on Circuits and Systems for Video Technology, 34 (4). p. 2000. doi:10.1109/tcsvt.2022.3202810 ISSN 1558-2205.
|
PDF
WRAP-ESGN-efficient-stereo-geometry-network-fast-3D-object-detection-Shao-2022.pdf - Accepted Version - Requires a PDF viewer. Download (2955Kb) | Preview |
Official URL: https://doi.org/10.1109/tcsvt.2022.3202810
Abstract
Fast stereo based 3D object detectors have made great progress recently. However, they suffer from the inferior accuracy. We argue that the main reason is due to the poor geometry-aware feature representation in 3D space. To solve this problem, we propose an efficient stereo geometry network (ESGN). The key in our ESGN is an efficient geometry-aware feature generation (EGFG) module. Our EGFG module first uses a stereo correlation and reprojection module to construct multi-scale stereo volumes in camera frustum space, second employs a multi-scale bird’s eye view (BEV) projection and fusion module to generate multiple geometry-aware features. In these two steps, we adopt deep multi-scale information fusion for discriminative geometry-aware feature generation, without any complex aggregation networks. In addition, we introduce a deep geometry-aware feature distillation scheme to guide stereo feature learning with a LiDAR-based detector. The experiments are performed on the classical KITTI dataset. On KITTI test set, our ESGN outperforms the fast state-of-art-art detector YOLOStereo3D by 5.14% on mAP3d at 62ms. To the best of our knowledge, our ESGN achieves a best trade-off between accuracy and speed. We hope that our efficient stereo geometry network can provide more possible directions for fast 3D object detection.
Item Type: | Journal Article | ||||||||
---|---|---|---|---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | ||||||||
SWORD Depositor: | Library Publications Router | ||||||||
Journal or Publication Title: | IEEE Transactions on Circuits and Systems for Video Technology | ||||||||
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) | ||||||||
ISSN: | 1558-2205 | ||||||||
Official Date: | April 2024 | ||||||||
Dates: |
|
||||||||
Volume: | 34 | ||||||||
Number: | 4 | ||||||||
Page Range: | p. 2000 | ||||||||
DOI: | 10.1109/tcsvt.2022.3202810 | ||||||||
Status: | Peer Reviewed | ||||||||
Publication Status: | Published | ||||||||
Re-use Statement: | © 2022 Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | ||||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||||
Date of first compliant deposit: | 14 November 2022 | ||||||||
Date of first compliant Open Access: | 14 November 2022 |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year