CenterNet3D: An Anchor Free Object Detector for Point Cloud

doi:10.1109/TITS.2021.3118698

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	CenterNet3D: An Anchor Free Object Detector for Point Cloud
	Wang, Guojun 1; Wu, Jian 1; Tian, Bin2,3 ; Teng, Siyu 4; Chen, Long 5; Cao, Dongpu 6
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
	2021-10-14
页码	13
通讯作者	Tian, Bin(bin.tian@ia.ac.cn)
摘要	Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are inefficient and require additional post-processing. In this paper, we eliminate anchors and model an object as a single point--the center point of its bounding box. Based on the center point, we propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Our CenterNet3D uses keypoint estimation to find center points and directly regresses 3D bounding boxes. However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries. To solve this issue, we propose an extra corner attention module to enforce the CNN backbone to pay more attention to object boundaries. Besides, considering that one-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient keypoint-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed CenterNet3D is non-maximum suppression free which makes it more efficient and simpler. We evaluate CenterNet3D on the widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art anchor-based one-stage methods and has comparable performance to two-stage methods as well. It has an inference speed of 20 FPS and achieves the best speed and accuracy trade-off. Our source code will be released at https://github.com/wangguojun2018/CenterNet3d.
关键词	Three-dimensional displays Feature extraction Detectors Object detection Proposals Laser radar Heating systems Point cloud autonomous vehicles deep learning 3D detection anchor free
DOI	10.1109/TITS.2021.3118698
收录类别	SCI
语种	英语
资助项目	Key-Area Research and Development Program of Guangdong Province[2020B090921003] ; Key-Area Research and Development Program of Guangdong Province[2020B0909050001] ; National Natural Science Foundation of China[61503380] ; National Natural Science Foundation of China[61773381]
项目资助者	Key-Area Research and Development Program of Guangdong Province ; National Natural Science Foundation of China
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000733458300001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	人工智能+交通
引用统计	被引频次：13[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/46945
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Tian, Bin
作者单位	1.Jilin Univ, State Key Lab Automot Simulat & Control, Changchun 130022, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 4.Hong Kong Baptist Univ, Dept Comp Sci, Hong Kong, Peoples R China 5.Sun Yat Sen Univ, Sch Data & Comp Sci, Guangzhou 510275, Guangdong, Peoples R China 6.Univ Waterloo, Dept Mech & Mechatron Engn, Waterloo, ON N2L 3G1, Canada
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wang, Guojun,Wu, Jian,Tian, Bin,et al. CenterNet3D: An Anchor Free Object Detector for Point Cloud[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2021:13.
APA	Wang, Guojun,Wu, Jian,Tian, Bin,Teng, Siyu,Chen, Long,&Cao, Dongpu.(2021).CenterNet3D: An Anchor Free Object Detector for Point Cloud.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,13.
MLA	Wang, Guojun,et al."CenterNet3D: An Anchor Free Object Detector for Point Cloud".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021):13.