SARPNET: Shape attention regional proposal network for liDAR-based 3D object detection
文献类型：期刊论文
| 作者 | Ye, Yangyang1; Chen, Houjin1; Zhang, Chi2 ; Hao, Xiaoli1; Zhang, Zhaoxiang2
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2020-02-28 |
| 卷号 | 379页码:53-63 |
| 关键词 | Shape attention 3D shape priors Feature encoder 3D object detection LiDAR point cloud |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2019.09.086 |
| 通讯作者 | Chen, Houjin(hjchen@bjtu.edu.cn) |
| 英文摘要 | Real-time 3D object detection is a fundamental technique in numerous applications, such as autonomous driving, unmanned aerial vehicles (UAV) and robot vision. However, current LiDAR-based 3D object detection algorithms allocate inadequate attention to the inhomogeneity of LiDAR point clouds and the shape encoding capability of regional proposal schemes. This paper introduces a novel 3D object detection network called the Shape Attention Regional Proposal Network (SARPNET), which deploys a new low-level feature encoder to remedy the sparsity and inhomogeneity of LiDAR point clouds with an even sample method, and embodies a shape attention mechanism that learns the statistic 3D shape priors of objects and uses them to spatially enhance semantic embeddings. Experimental results show that the proposed one-stage method outperforms state-of-the-art one-stage and even two-stage methods on the KITTI 3D object detection benchmark. It achieved a BEV AP of (87.26%, 62.80%), 3D AP of (75.64%, 60.43%), and orientation AP of (88.86%, 71.01%) for the detection of cars and cyclists, respectively. Besides, the method is the third winner in the nuScenes 3D Detection challenge of CVPR2019 Workshop on Autonomous Driving (WAD). (C) 2019 Elsevier B.V. All rights reserved. |
| 资助项目 | National Key R&D Program of China[2018YFB1004600] ; Beijing Municipal Natural Science Foundation[Z181100008918010] ; National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[61761146004] ; National Natural Science Foundation of China[61602481] ; National Natural Science Foundation of China[61773375] ; National Natural Science Foundation of China[61771042] ; Fundamental Research Funds of BJTU[2017JBZ002] ; Microsoft Collaborative Research Project |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000507464700005 |
| 出版者 | ELSEVIER |
| 资助机构 | National Key R&D Program of China ; Beijing Municipal Natural Science Foundation ; National Natural Science Foundation of China ; Fundamental Research Funds of BJTU ; Microsoft Collaborative Research Project |
| 源URL | [http://ir.ia.ac.cn/handle/173211/29501]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Chen, Houjin |
| 作者单位 | 1.Beijing Jiaotong Univ, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Ye, Yangyang,Chen, Houjin,Zhang, Chi,et al. SARPNET: Shape attention regional proposal network for liDAR-based 3D object detection[J]. NEUROCOMPUTING,2020,379:53-63. |
| APA | Ye, Yangyang,Chen, Houjin,Zhang, Chi,Hao, Xiaoli,&Zhang, Zhaoxiang.(2020).SARPNET: Shape attention regional proposal network for liDAR-based 3D object detection.NEUROCOMPUTING,379,53-63. |
| MLA | Ye, Yangyang,et al."SARPNET: Shape attention regional proposal network for liDAR-based 3D object detection".NEUROCOMPUTING 379(2020):53-63. |
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。