CenterNet3D: An Anchor Free Object Detector for Point Cloud

doi:10.1109/TITS.2021.3118698

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进控制与自动化团队

	CenterNet3D: An Anchor Free Object Detector for Point Cloud
	Wang, Guojun 6; Wu, Jian 6; Tian, Bin 2,3; Teng, Siyu 4; Chen, Long 1; Cao, Dongpu 5
刊名	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
	2021-10-14
页码	13
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
ISSN号	1524-9050
DOI	10.1109/TITS.2021.3118698
通讯作者	Tian, Bin(bin.tian@ia.ac.cn)
英文摘要	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.
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]
WOS研究方向	Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000733458300001
资助机构	Key-Area Research and Development Program of Guangdong Province ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/46944]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者	Tian, Bin
作者单位	1.Sun Yat Sen Univ, Sch Data & Comp Sci, Guangzhou 510275, Guangdong, 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.Univ Waterloo, Dept Mech & Mechatron Engn, Waterloo, ON N2L 3G1, Canada 6.Jilin Univ, State Key Lab Automot Simulat & Control, Changchun 130022, Peoples R China
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.