Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss

doi:10.1109/TNNLS.2020.3028964

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 > 深度强化学习

	Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss
	Chen, Yaran 2,3; Li, Haoran 2,3; Gao, Ruiyuan 1; Zhao, Dongbin 2,3
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2022-02-01
卷号	33 期号:2 页码:762-773
关键词	3-D object detection generalized Intersection of Union (GIoU) loss segmentation
ISSN号	2162-237X
DOI	10.1109/TNNLS.2020.3028964
通讯作者	Zhao, Dongbin(dongbin.zhao@ia.ac.cn)
英文摘要	The 3-D object detection is crucial for many real-world applications, attracting many researchers' attention. Beyond 2-D object detection, 3-D object detection usually needs to extract appearance, depth, position, and orientation information from light detection and ranging (LiDAR) and camera sensors. However, due to more degrees of freedom and vertices, existing detection methods that directly transform from 2-D to 3-D still face several challenges, such as exploding increase of anchors' number and inefficient or hard-to-optimize objective. To this end, we present a fast segmentation method for 3-D point clouds to reduce anchors, which can largely decrease the computing cost. Moreover, taking advantage of 3-D generalized Intersection of Union (GIoU) and L-1 losses, we propose a fused loss to facilitate the optimization of 3-D object detection. A series of experiments show that the proposed method has alleviated the abovementioned issues effectively.
资助项目	National Natural Science Foundation of China (NSFC)[62006226] ; Natural Science Foundation of Beijing[L191002]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000752016400027
资助机构	National Natural Science Foundation of China (NSFC) ; Natural Science Foundation of Beijing
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/47349]
专题	复杂系统管理与控制国家重点实验室_深度强化学习
通讯作者	Zhao, Dongbin
作者单位	1.Chinese Univ Hong Kong, Dept Comp Sci & Engn, Shatin, Hong Kong, 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, Coll Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Chen, Yaran,Li, Haoran,Gao, Ruiyuan,et al. Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022,33(2):762-773.
APA	Chen, Yaran,Li, Haoran,Gao, Ruiyuan,&Zhao, Dongbin.(2022).Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,33(2),762-773.
MLA	Chen, Yaran,et al."Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 33.2(2022):762-773.