混合l<sub>2</sub>/l<sub>1/2</sub>范数的局部组稀疏表示方法

doi:10.16451/j.cnki.issn1003-6059.201809001

摘要
图/表
参考文献(0)
相关文章 (15)

全文: PDF (1774 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

当前基于稀疏表示的行人再识别都是通过松弛l₀正则项为l₁正则项以达到逼近l₀范数稀疏性的目的.在满足有限等距性质(RIP)条件下,l₁和l₀具有等价性,然而在具有杂乱背景、物体遮挡等众多干扰因素的行人再识别任务中,却很难满足RIP条件.因此,文中提出混合l₂/l_1/2范数的组稀疏表示方法,通过将gallery集中同一行人图像序列视为一组,利用l₂范数约束组内结构,l_1/2范数约束组间结构,对遮挡和杂乱背景等干扰因素具有更高的鲁棒性.为了进一步增强模型的判别性,引入人体结构约束,将行人图像划分为若干近邻块区域,针对每一区域分别构造适应性的混合l₂/l_1/2范数的组稀疏模型,最终融合全部稀疏模型得出再识别结果.在当前具有挑战性的2个多行人图像序列数据集PRID 2011和iLIDS-VID上的实验验证文中方法的有效性.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李小宝
	郭立君
	张荣
	洪金华

关键词 ：行人再识别, 稀疏表示, 组稀疏, 范数

Abstract：

In the existing person re-identification approaches based on sparse representation, l₁ regularization is generally utilized to approximate l₀-norm sparsity. Under the restricted isometry property (RIP) conditions, the l₀ regularization is equivalent to the l₁ regularization. However, it is difficult to meet the RIP conditions in person re-identification with many disturbing factors, such as cluttered background and object occlusion. In this paper, a group sparse representation method with mixed l₂/l_1/2-norm is proposed. The identical person image sequence in the gallery is regarded as a group, the intra-group structure is constrained by l₂-norm, and the inter-group structure is constrained by l_1/2-norm. The resulting model is more robust to the occlusion and cluttered backgrounds. The human body structure constraint is introduced to further enhance the discriminability of the proposed model. The person image is divided into several neighboring block regions. An adaptive sparse model of mixed l₂/l_1/2 norm is constructed for each region. Finally, the several sparse models are merged to identify persons. Experiments on PRID 2011 and iLIDS-VID datasets verify the effectiveness of the proposed model.

Key words： Person Re-identification Sparse Representation Group Sparse Norm

收稿日期: 2018-04-23

ZTFLH:

TP 391

基金资助:

浙江省自然科学基金项目(No.LY17F030002)、浙江省公益技术研究计划项目(No.LGF18F020007)资助

作者简介: 李小宝，硕士研究生，主要研究方向为计算机视觉、模式识别.E-mail：xiaobaoli15@163.com.郭立君（通讯作者），博士，教授，主要研究方向为计算机视觉、模式识别、移动互联网及其应用.E-mail：guolijun@nbu.edu.cn.张荣，博士，副教授，主要研究方向为数字取证、信息安全.E-mail：zhangrong@nbu.edu.cn.洪金华，硕士研究生，主要研究方向为计算机视觉、模式识别.E-mail：326437423@qq.com.

引用本文:

李小宝，郭立君，张荣，洪金华. 混合l₂/l_1/2范数的局部组稀疏表示方法[J]. 模式识别与人工智能, 2018, 31(9): 773-785. LI Xiaobao, GUO Lijun, ZHANG Rong, HONG Jinhua. Local Group Sparse Representation with Mixed l₂/l_1/2 Norm. , 2018, 31(9): 773-785.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201809001 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2018/V31/I9/773

[1] ZHAO R,OUYANG W L,WANG X G. Unsupervised Salience Learning for Person Re identification // Proc of the IEEE Confe rence on Computer Vision and Pattern Recognition.Washington, USA: IEEE, 2013: 3586-3593.
[2] FARENZENA M, BAZZANI L, PERINA A,et al.Person Re id entification by Symmetry Driven Accumulation of Local Features // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington, USA: IEEE, 2010: 2360-2367..
[3] LIAO S C, HU Y, ZHU X Y,et al. Person Re identification by Local Maximal Occurrence Representation and Metric Learning // Proc of the IEEE Conference on Computer Vision and Pattern Re cognition . Washington, USA: IEEE, 2015: 2197-2206..
[4] GUILLAUMIN M, VERBEEK J, SCHMID C. Is That You? Metric Learning Approaches for Face Identification // Proc of the 12th IEEE International Conference on Computer Vision.Washington, USA: IEEE, 2009: 498-505..
[5] PROSSER B, ZHANG W C, GONG S G,et al.Person Re identification by Support Vector Ranking // Proc of the British Machine Vision Conference. London, UK: BMVA, 2010. DOI: 10.5244/C.24.21..
[6] WANG T Q, GONG S G, ZHU X T,et al.Person Re identification by Video Ranking // Proc of the European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014: 688-703..
[7] SIMONNET D, LEWANDOWSKI M, VELASTIN S A,et al. Re identification of Pedestrians in Crowds Using Dynamic Time Warping // Proc of the European Conference on Computer Vision. Florence, Italy: Springer, 2012: 423-432..
[8] NIXON M S, TAN T N, CHELLAPPA R. Human Identification Based on Gait. Majlesi Journal of Electrical Engineering, 2008,2(3): 15-23..
[9] WRIGHT J, YANG A Y, GANESH A,et al. Robust Face Recognition via Sparse Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227.
[10] AGARWAL S, ROTH D. Learning a Sparse Representation for Object Detection // Proc of the 7th European Conference on Computer Vision. Copenhagen, Denmark: Springer, 2002: 113-130.
[11] KHEDHER M I, EL YACOUBI M A, DORIZZI B. Multi shot SURF Based Person Re identification via Sparse Representation // Proc of the 10th IEEE International Conference on Advanced Video and Signal Based Surveillance. Washington, USA: IEEE, 2013: 159-164.
[12] LISANTI G, MASI I, BAGDANOV A D,et al.Person Re identification by Iterative Re weighted Sparse Ranking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(8): 1629-1642.
[13] KARANAM S, LI Y, RADKE R J. Person Re identification with Block Sparse Recovery. Image and Vision Computing, 2017, 60: 75-90.
[14] AN L, CHEN X J, YANG S F,et al. Sparse Representation Ma tching for Person Re identification. Information Sciences, 2016, 355/356: 74-89.
[15] XU Z B, ZHANG H, WANG Y,et al.L1/2 Regularization. Science China(Information Sciences), 2010, 53(6): 1159-1169.
[16] TIBSHIRANI R. Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society(Methodological), 1996, 58(1): 267-288.
[17] DONOHO D L, HUO X. Uncertainty Principles and Ideal Atomic Decomposition. IEEE Transactions on Information Theory, 2001, 47(7): 2845-2862.
[18] ELAD M, BRUCKSTERIN A M. A Generalized Uncertainty Principle and Sparse Representation in Pairs of Bases. IEEE Transactions on Information Theory, 2002, 48(9): 2558-2567.
[19] DENG W, YIN W T, ZHANG Y. Group Sparse Optimization by Alternating Direction Method. Technical Report, TR11-06. Houston, USA: Rice University Computational and Applied Mathema tics , 2011.
[20] PARIKH N, BOYD S. Proximal Algorithms. Foundations & Tr ends in Optimization, 2014, 1(3): 123-231.
[21] BAK S, CARR P. Person Re identification Using Deformable Pa tch Metric Learning // Proc of the IEEE Winter Conference on Applications of Computer Vision.New York, USA: IEEE, 2016: 1-9.
[22] XIONG F, GOU M R, CAMPS O,et al.Person Re identification Using Kernel Based Metric Learning Methods // Proc of the European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014: 1-16.
[23] SUGIYAMA M. Local Fisher Discriminant Analysis for Supervised Dimensionality Reduction // Proc of the 23rd International Confe rence on Machine Learning. New York, USA: ACM, 2006: 905-912.
[24] HIRZER M, BELEZNAI C, ROTH P M,et al. Person Re identification by Descriptive and Discriminative Classification // Proc of the Scandinavian Conference on Image Analysis. Berlin, Germany: Springer, 2011: 91-102.
[25] MATSUKAWA T, OKABE T, SUZUKI E,et al.Hierarchical Gaussian Descriptor for Person Re identification // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 1363-1372.
[26] KARANAM S, WU Z, RADKE R J. Learning Affine Hull Representations for Multi shot Person Re identification [J/OL]. [2018-03-25]. https://ieeexplore.ieee.org/stamp/stamp.jsp？
[27] ZHENG A H, ZHANG X H, JIANG B,et al.A Subspace Learn-ing Approach to Multishot Person Reidentification [J/OL]. [2018-03-25]. https://ieeexplore.ieee.org/stamp/stamp.jsp？
[28] KARANAM S, GOU M, WU Z Y,et al.A Systematic Evaluation and Benchmark for Person Re identification: Features, Metrics, and Datasets [J/OL]. [2018-03-25]. https://arxiv.org/pdf/1605.09653v3.pdf.
[29] LI Y, WU Z Y, KARANAM S,et al. Multi shot Human Re identification Using Adaptive Fisher Discriminant Analysis // Proc of the British Machine Vision Conference. London, UK: BMVA, 2015. DOI: 10.5244/C.19.73.
[30] KARANAM S, LI Y, RADKE R J. Person Re identification with Discriminatively Trained Viewpoint Invariant Dictionaries // Proc of the IEEE International Conference on Computer Vision. Wa shington , USA: IEEE, 2015: 4516-4524.