Attributes Guided Feature Learning for Vehicle Re-Identification

doi:10.1109/TETCI.2021.3127906

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Attributes Guided Feature Learning for Vehicle Re-Identification
	Li, Hongchao 4; Lin, Xianmin 4; Zheng, Aihua 3; Li, Chenglong 3; Luo, Bin 4; He, Ran 2; Hussain, Amir 1
刊名	IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
	2021-11-30
页码	11
关键词	Feature extraction Cameras Color Image color analysis Task analysis Training Semantics Attributes deep features vehicle re-identification
ISSN号	2471-285X
DOI	10.1109/TETCI.2021.3127906
通讯作者	Luo, Bin(ahu_lb@163.com)
英文摘要	Vehicle Re-ID has recently attracted enthusiastic attention due to its potential applications in smart city and urban surveillance. However, it suffers from large intra-class variation caused by view variations and illumination changes, and inter-class similarity especially for different identities with a similar appearance. To handle these issues, in this paper, we propose a novel deep network architecture, which guided by meaningful attributes including camera views, vehicle types and colors for vehicle Re-ID. In particular, our network is end-to-end trained and contains three subnetworks of deep features embedded by the corresponding attributes. For network training, we annotate the view labels on the VeRi-776 dataset. Note that one can directly adopt the pre-trained view (as well as type and color) subnetwork on the other datasets with only ID information, which demonstrates the generalization of our model. Extensive experiments on the benchmark datasets VeRi-776 and VehicleID suggest that the proposed approach achieves the promising performance and yields to a new state-of-the-art for vehicle Re-ID.
资助项目	National Key Research and Development Program of China[2018AAA0100400] ; National Natural Science Foundation of China[61976002] ; National Natural Science Foundation of China[61976003] ; National Natural Science Foundation of China[62076003] ; National Natural Science Foundation of China[61860206004]
WOS关键词	PERSON REIDENTIFICATION ; NETWORK
WOS研究方向	Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000727918400001
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/46797]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Luo, Bin
作者单位	1.Edinburgh Napier Univ, Sch Comp, Edinburgh EH10 5DT, Midlothian, Scotland 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Anhui Univ, Sch Artificial Intelligence, Anhui Prov Key Lab Multimodal Cognit Computat, Informat Mat & Intelligent Sensing Lab Anhui Prov, Hefei 230601, Peoples R China 4.Anhui Univ, Sch Comp Sci & Technol, Hefei 230601, Peoples R China
推荐引用方式 GB/T 7714	Li, Hongchao,Lin, Xianmin,Zheng, Aihua,et al. Attributes Guided Feature Learning for Vehicle Re-Identification[J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE,2021:11.
APA	Li, Hongchao.,Lin, Xianmin.,Zheng, Aihua.,Li, Chenglong.,Luo, Bin.,...&Hussain, Amir.(2021).Attributes Guided Feature Learning for Vehicle Re-Identification.IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE,11.
MLA	Li, Hongchao,et al."Attributes Guided Feature Learning for Vehicle Re-Identification".IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2021):11.