中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 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

文献类型：期刊论文

作者Guan, He1,2; Song, Chunfeng1,2; Zhang, Zhaoxiang1,2
刊名FRONTIERS OF COMPUTER SCIENCE
出版日期2024-10-01
卷号18期号:5页码:9
ISSN号2095-2228
关键词3D detection monocular augmentation geometry
DOI10.1007/s11704-023-3242-2
通讯作者Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
英文摘要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.
资助项目National 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]
WOS研究方向Computer Science
语种英语
出版者HIGHER EDUCATION PRESS
WOS记录号WOS:001142745300001
资助机构National Key R&D Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/54816]  
专题多模态人工智能系统全国重点实验室
通讯作者Zhang, Zhaoxiang
作者单位1.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
推荐引用方式
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。