OS-DS tracker: Orientation-variant Siamese 3D tracking with Detection based Sampling

doi:10.1016/j.patrec.2023.08.021

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	OS-DS tracker: Orientation-variant Siamese 3D tracking with Detection based Sampling
	Zhang, Qiuyu 1; Wang, Lipeng 1; Li, Wanyi 2; Meng, Hao 1; Zhang, Wen 1; Zhang, Zhi 1; Wang, Peng 2
刊名	PATTERN RECOGNITION LETTERS
	2023-10-01
卷号	174 页码:7
关键词	LIDAR point clouds Object tracking Gaussian sampling Candidate regions Auto-encoder
ISSN号	0167-8655
DOI	10.1016/j.patrec.2023.08.021
通讯作者	Wang, Lipeng(wanglipeng@hrbeu.edu.cn)
英文摘要	LIDAR point clouds are less affected by the weather and possess more depth of field than 2D images. However, sparsity and disorder of point clouds bring challenges for 3D object tracking due to the difficulty in detecting and encoding. In addition, ineffective candidate proposals increase the phenomenon of the loss of target tracking or wrong target tracking. In this paper, we propose an Orientation-variant Siamese 3D object tracking network that utilizes a Detection based Sampling module to generate candidate proposals (OS-DS tracker). The Detection based Sampling module is used to cut the excessive and useless proposals. And the multivariate Gaussian sampling generates the candidate proposals when the objects are not detected. Concretely, we first pre-train PointRCNN Network to globally detect objects from LIDAR point clouds. Then the 3D detected objects are refined by Candidate Regions Sampling to generate candidate proposals. Meanwhile, to make the feature vectors more discriminative, we design an Orientation-variant Siamese Auto-encoder, i.e., tracking loss regress to the intersection over union (IOU) of the template box and the candidate region boxes. Our method is tested on the KITTI dataset and the SHIP Tracking dataset. Compared with the previous state-of-the-arts, the proposed method outperforms in vessel tracking with 5.2%/2.1% improvement in Success and Precision.
资助项目	National Natural Science Founda-tion of China[62173103] ; National Natural Science Founda-tion of China[52171299] ; Fundamental Re-search Funds for the Central Universities of China[3072022JC0402] ; Fundamental Re-search Funds for the Central Universities of China[3072022JC0403]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:001075309400001
资助机构	National Natural Science Founda-tion of China ; Fundamental Re-search Funds for the Central Universities of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53101]
专题	多模态人工智能系统全国重点实验室
通讯作者	Wang, Lipeng
作者单位	1.Harbin Engn Univ, Coll Intelligent Syst Sci & Engn, Harbin 150001, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Qiuyu,Wang, Lipeng,Li, Wanyi,et al. OS-DS tracker: Orientation-variant Siamese 3D tracking with Detection based Sampling[J]. PATTERN RECOGNITION LETTERS,2023,174:7.
APA	Zhang, Qiuyu.,Wang, Lipeng.,Li, Wanyi.,Meng, Hao.,Zhang, Wen.,...&Wang, Peng.(2023).OS-DS tracker: Orientation-variant Siamese 3D tracking with Detection based Sampling.PATTERN RECOGNITION LETTERS,174,7.
MLA	Zhang, Qiuyu,et al."OS-DS tracker: Orientation-variant Siamese 3D tracking with Detection based Sampling".PATTERN RECOGNITION LETTERS 174(2023):7.