CASIA OpenIR  > 多模态人工智能系统全国重点实验室
GRAMO: geometric resampling augmentation for monocular 3D object detection
Guan, He1,2; Song, Chunfeng1,2; Zhang, Zhaoxiang1,2
Source PublicationFRONTIERS OF COMPUTER SCIENCE
ISSN2095-2228
2024-10-01
Volume18Issue:5Pages:9
Abstract

Data augmentation is widely recognized as an effective means of bolstering model robustness. However, when applied to monocular 3D object detection, non-geometric image augmentation neglects the critical link between the image and physical space, resulting in the semantic collapse of the extended scene. To address this issue, we propose two geometric-level data augmentation operators named Geometric-Copy-Paste (Geo-CP) and Geometric-Crop-Shrink (Geo-CS). Both operators introduce geometric consistency based on the principle of perspective projection, complementing the options available for data augmentation in monocular 3D. Specifically, Geo-CP replicates local patches by reordering object depths to mitigate perspective occlusion conflicts, and Geo-CS re-crops local patches for simultaneous scaling of distance and scale to unify appearance and annotation. These operations ameliorate the problem of class imbalance in the monocular paradigm by increasing the quantity and distribution of geometrically consistent samples. Experiments demonstrate that our geometric-level augmentation operators effectively improve robustness and performance in the KITTI and Waymo monocular 3D detection benchmarks.

Keyword3D detection monocular augmentation geometry
DOI10.1007/s11704-023-3242-2
Indexed BySCI
Language英语
Funding ProjectNational Key R&D Program of China[2022ZD0160102] ; National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[U21B2042] ; National Natural Science Foundation of China[62072457] ; National Natural Science Foundation of China[62006231]
Funding OrganizationNational Key R&D Program of China ; National Natural Science Foundation of China
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS IDWOS:001142745300001
PublisherHIGHER EDUCATION PRESS
Sub direction classification三维视觉
planning direction of the national heavy laboratory脑启发多模态智能模型与算法
Paper associated data
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/54817
Collection多模态人工智能系统全国重点实验室
Corresponding AuthorZhang, Zhaoxiang
Affiliation1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, State Key Lab Multimodal Artificial Intelligence S, Inst Automat, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Guan, He,Song, Chunfeng,Zhang, Zhaoxiang. GRAMO: geometric resampling augmentation for monocular 3D object detection[J]. FRONTIERS OF COMPUTER SCIENCE,2024,18(5):9.
APA Guan, He,Song, Chunfeng,&Zhang, Zhaoxiang.(2024).GRAMO: geometric resampling augmentation for monocular 3D object detection.FRONTIERS OF COMPUTER SCIENCE,18(5),9.
MLA Guan, He,et al."GRAMO: geometric resampling augmentation for monocular 3D object detection".FRONTIERS OF COMPUTER SCIENCE 18.5(2024):9.
Files in This Item: Download All
File Name/Size DocType Version Access License
GRAMO.pdf(2242KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Guan, He]'s Articles
[Song, Chunfeng]'s Articles
[Zhang, Zhaoxiang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Guan, He]'s Articles
[Song, Chunfeng]'s Articles
[Zhang, Zhaoxiang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Guan, He]'s Articles
[Song, Chunfeng]'s Articles
[Zhang, Zhaoxiang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: GRAMO.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.