Object Reidentification via Joint Quadruple Decorrelation Directional Deep Networks in Smart Transportation

doi:10.1109/JIOT.2020.2963996

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	Object Reidentification via Joint Quadruple Decorrelation Directional Deep Networks in Smart Transportation
	Zhu, Jianqing 1; Huang, Jingchang 2; Zeng, Huanqiang 3; Ye, Xiaoqing 2; Li, Baoqing 2; Lei, Zhen4 ; Zheng, Lixin 1
发表期刊	IEEE INTERNET OF THINGS JOURNAL
ISSN	2327-4662
	2020-04-01
卷号	7 期号:4 页码:2944-2954
通讯作者	Zeng, Huanqiang(zeng0043@hqu.edu.cn)
摘要	Object reidentification with the goal of matching pedestrian or vehicle images captured from different camera viewpoints is of considerable significance to public security. Quadruple directional deep learning features (QD-DLFs) can comprehensively describe object images. However, the correlation among QD-DLFs is an unavoidable problem, since QD-DLFs are learned with quadruple independent directional deep networks (QIDDNs) driven with the same training data, and each network holds the same basic deep feature learning architecture (BDFLA). The correlation among QD-DLFs is harmful to the complementarity of QD-DLFs, restricting the object reidentification performance. For that, we propose joint quadruple decorrelation directional deep networks (JQD(3)Ns) to reduce the correlation among the learned QD-DLFs. In order to jointly train JQD(3)Ns, besides the softmax loss functions, a parameter correlation cost function is proposed to indirectly reduce the correlation among QD-DLFs by enlarging the dissimilarity among the parameters of JQD(3)Ns. Extensive experiments on three publicly available large-scale data sets demonstrate that the proposed JQD(3)Ns approach is superior to multiple state-of-the-art object reidentification methods.
关键词	Deep learning pedestrian reidentification smart transportation vehicle reidentification
DOI	10.1109/JIOT.2020.2963996
关键词[WOS]	PERSON REIDENTIFICATION ; VEHICLE REIDENTIFICATION ; IOT ; FINGERPRINT ; INTERNET
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61976098] ; National Natural Science Foundation of China[61602191] ; National Natural Science Foundation of China[61871434] ; National Natural Science Foundation of China[61802136] ; National Natural Science Foundation of China[61876178] ; Natural Science Foundation of Fujian Province[2018J01090] ; Natural Science Foundation for Outstanding Young Scholars of Fujian Province[2019J06017] ; Open Foundation of Key Laboratory of Security Prevention Technology and Risk Assessment, People's Public Security University of China[18AFKF11] ; Key Science and Technology Project of Xiamen City[3502ZCQ20191005] ; Science and Technology Bureau of Quanzhou[2018C115R] ; Science and Technology Bureau of Quanzhou[2017G027] ; Science and Technology Bureau of Quanzhou[2017G036] ; Promotion Program for Young and Middle-Aged Teacher in Science and Technology Research of Huaqiao University[ZQN-PY418] ; Promotion Program for Young and Middle-Aged Teacher in Science and Technology Research of Huaqiao University[ZQN-YX403] ; Scientific Research Funds of Huaqiao University[16BS108] ; Scientific Research Funds of Huaqiao University[14BS201] ; Scientific Research Funds of Huaqiao University[14BS204]
项目资助者	National Natural Science Foundation of China ; Natural Science Foundation of Fujian Province ; Natural Science Foundation for Outstanding Young Scholars of Fujian Province ; Open Foundation of Key Laboratory of Security Prevention Technology and Risk Assessment, People's Public Security University of China ; Key Science and Technology Project of Xiamen City ; Science and Technology Bureau of Quanzhou ; Promotion Program for Young and Middle-Aged Teacher in Science and Technology Research of Huaqiao University ; Scientific Research Funds of Huaqiao University
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000537136400039
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：9[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/173211/39631
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
通讯作者	Zeng, Huanqiang
作者单位	1.Huaqiao Univ, Coll Engn, Quanzhou 362021, Peoples R China 2.Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Shanghai 201314, Peoples R China 3.Huaqiao Univ, Coll Informat Sci & Engn, Xiamen 361021, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Jianqing,Huang, Jingchang,Zeng, Huanqiang,et al. Object Reidentification via Joint Quadruple Decorrelation Directional Deep Networks in Smart Transportation[J]. IEEE INTERNET OF THINGS JOURNAL,2020,7(4):2944-2954.
APA	Zhu, Jianqing.,Huang, Jingchang.,Zeng, Huanqiang.,Ye, Xiaoqing.,Li, Baoqing.,...&Zheng, Lixin.(2020).Object Reidentification via Joint Quadruple Decorrelation Directional Deep Networks in Smart Transportation.IEEE INTERNET OF THINGS JOURNAL,7(4),2944-2954.
MLA	Zhu, Jianqing,et al."Object Reidentification via Joint Quadruple Decorrelation Directional Deep Networks in Smart Transportation".IEEE INTERNET OF THINGS JOURNAL 7.4(2020):2944-2954.