Knowledge Commons of Institute of Automation,CAS
GRAMO: geometric resampling augmentation for monocular 3D object detection | |
Guan, He1,2![]() ![]() ![]() | |
发表期刊 | FRONTIERS OF COMPUTER SCIENCE
![]() |
ISSN | 2095-2228 |
2024-10-01 | |
卷号 | 18期号:5页码:9 |
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. |
关键词 | 3D detection monocular augmentation geometry |
DOI | 10.1007/s11704-023-3242-2 |
收录类别 | SCI |
语种 | 英语 |
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] |
项目资助者 | National Key R&D Program of China ; National Natural Science Foundation of China |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods |
WOS记录号 | WOS:001142745300001 |
出版者 | HIGHER EDUCATION PRESS |
七大方向——子方向分类 | 三维视觉 |
国重实验室规划方向分类 | 脑启发多模态智能模型与算法 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/54817 |
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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
GRAMO.pdf(2242KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论