基于局部突出性稠密块匹配的人体重现

doi:10.3969/j.issn.1000-3428.2016.06.048

摘要/Abstract

摘要： 人体重现是人体目标提取及跟踪中的关键技术,目前多数方法都是通过提取人体表观特征并计算特征相似度来实现人体匹配,对表观特征差异较大的图像识别准确率较高,但不适用于表观特征相似的图像。考虑到同一行人不同图像的表观特征局部结构信息比不同行人相似图像表现得更相似,提出一种基于局部突出性稠密块匹配的人体重现算法。提取每个稠密块的组合特征,计算每块在局部区域里的相似性,并据此确定其在局部区域里的突出权重。在VIPeR和CUHK数据库上的实验结果表明,该方法识别率较高,对视觉、姿势和光照的变化具有强鲁棒性,并且对多数表观特征相似的行人也能给出准确的匹配结果。

关键词: 人体重现, 目标提取, 表观特征, 局部结构信息, 稠密块匹配, 局部突出性

Abstract: Person re-identification is the key technology in human object extraction and tracking.Now,mostly person re-identification methods extract the human appearance feature and compute the feature similarity to implement the human matching.These methods can get accurate results for the images which have apparent differnce,but they are difficult to recognize images which have similar areas.Aiming at this problem,considering the region structure informations of the appearance feature in the different images of the same pedestrian are more similar than that in the similar images of different pedestrians,this paper proposes a person re-identification algorithm based on dense patch matching with local saliency.It extracts the combination feature of each dense block,calculates the similarity of each block in the local area and its saliency weight in local region according to the similarity.Experimental results on the VIPeR dataset and the CUHK dataset show that the proposed algorithm has higher recognition rate.It is invariant to the effects of variations of viewpoints,poses,lightings,and it can provide accurate matching results of pedestrians who have the most similar areas.

Key words: person re-identification, object extraction, appearance feature, local structure information, dense patch matching, local saliency

中图分类号:

TP391

柯伟扬,郭立君,张荣,王亚东. 基于局部突出性稠密块匹配的人体重现[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2016.06.048.

KE Weiyang,GUO Lijun,ZHANG Rong,WANG Yadong. Person Re-identification Based on Dense Patch Matching with Local Saliency[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2016.06.048.

http://www.ecice06.com/CN/Y2016/V42/I6/274

参考文献

参考文献［1］Ma Bingpeng,Su Yu,Jurie F.Local Descriptors Encoded by Fisher Vectors for Person Re-identification［C］//Proceedings of 2012 European Conference on Computer Vision.Berlin,Germany:Springer-Verlag,2012:413-422. ［2］Zheng Weishi,Gong Shaogang,Xiang Tao.Person Re-identification by Probabilistic Relative Distance Comparison［C］//Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2011:649-656. ［3］Bazzani L,Cristani M,Murino V.Symmetry-driven Accumulation of Local Features for Human Characteri-zation and Re-identification［J］.Computer Vision and Image Understanding,2013,117(2):130-144. ［4］Farenzena M,Bazzani L,Perina A,et al.Person Re-identification by Symmetry-driven Accumulation of Local Features［C］//Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:2360-2367. ［5］范彩霞,朱虹,蔺广逢,等.多特征融合的人体目标再识别［J］.中国图象图形学报,2013,18(6):711-717. ［6］Gray D,Tao Hai.Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features［M］//Forsyth D,Torr P,Zisserman A.Computer Vision-ECCV 2008.Berlin,Germany:Springer-Verlag,2008:262-275. ［7］Prosser B,Zheng Weishi,Gong Shaogong,et al.Person Re-identification by Support Vector Ranking［C］//Proceedings of 2010 British Machine Vision Conference.［S.l.］:BMVA Press,2010. ［8］Zhang Yunlong,Li Shutao.Gabor-LBP Based Region Covariance Descriptor for Person Re-identification［C］//Proceedings of the 6th International Conference on Image and Graphics.Washington D.C.,USA:IEEE Press,2011:368-371. ［9］Dikmen M,Akbas E,Huang T S,et al.Pedestrian Recognition with a Learned Metric［M］//Kimmel R,Klette R,Sugimoto A.Computer Vision-ACCV 2010.Berlin,Germany:Springer-Verlag,2011:501-512. ［10］Jüngling K,Bodensteiner C,Arens M.Person Re-identification in Multi-camera Networks［C］//Proceedings of 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2011:55-61. ［11］Cheng D S,Cristani M,Stoppa M,et al.Custom Pictorial Structures for Re-identification［C］//Pro-ceedings of 2011 British Machine Vision Conference.［S.l.］:BMVA Press,2011. ［12］Ayedi W,Snoussi H,Abid M.A Fast Multi-scale Covariance Descriptor for Object Re-identification［J］.Pattern Recognition Letters,2012,33(14):1902-1907. ［13］Zhao Rui,Ouyang Wanli,Wang Xiaogang.Unsupervised Salience Learning for Person Re-identification［C］//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.Wasghingtong D.C.,USA:IEEE Press,2013:3586-3593. ［14］Zhao Rui,Ouyang Wanli,Wang Xiaogang.Person Re-identification by Salience Matching［C］//Proceedings of 2013 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2013:2528-2535. ［15］陈普强,郭立君,张荣,等.基于全局空间约束块匹配的目标人体识别［J］.计算机研究与发展,2015,52(3):596-605. ［16］Pedagadi S,Orwell J,Velastin S,et al.Local Fisher Discriminant Analysis for Pedestrian Re-identification［C］//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3318 -3325. ［17］Yang Yi,Ramanan D.Articulated Pose Estimation with Flexible Mixtures-of-parts［C］//Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2011:1385-1392. ［18］Wang Xiaogang,Doretto G,Sebastian T,et al.Shape and Appearance Context Modeling［C］//Proceedings of the 11th IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2007:1-8. ［19］Li Wei,Wang Xiaogang.Locally Aligned Feature Transforms Across Views［C］//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3594-3601. ［20］Ma K,Ben-Arie J.Vector Array Based Multi-view Face Detection with Compound Exemplars［C］//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:3186-3193. ［21］Gray D,Brennan S,Tao Hai.Evaluating Appearance Models for Recognition,Reacquisition,and Tracking［C］//Proceedings of the 10th IEEE International Workshop on Performance Evaluation for Tracking and Surveillance.Washington D.C.,USA:IEEE Press,2007:47. ［22］Moon H,Phillips P J.Computational and Performance Aspects of PCA-based Face-recognition Algorithms［J］.Perception,2001,30(3):303-322. ［23］Koestinger M,Hirzer M,Wohlhart P,et al.Large Scale Metric Learning from Equivalence Constraints［C］//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:2288-2295. ［24］Mignon A,Jurie F.PCCA:A New Approach for Distance Learning from Sparse Pairwise Constraints［C］//Pro-ceesings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:2666-2672. 编辑金胡考

[1]	樊玮, 韩佳宁, 张宇翔. 基于网络表示学习的论文影响力预测算法[J]. 计算机工程, 2019, 45(12): 160-165,170.
[2]	吴晓秋,霍智勇. 室内场景的布局估计与目标区域提取算法[J]. 计算机工程, 2018, 44(8): 257-262,267.
[3]	宣晓,余勤. 加权截断p范数在运动目标检测中的应用[J]. 计算机工程, 2018, 44(6): 233-238,248.
[4]	吴礼洋,熊磊,仲柔在. 基于模糊聚类回归的人脸特征点定位研究[J]. 计算机工程, 2017, 43(8): 272-278,283.
[5]	冀续烨,陈明,冯国富,赵海乐. 一种多模型协同的目标提取方法[J]. 计算机工程, 2015, 41(5): 254-258,263.
[6]	孙慧, 石艳娇, 王建中, 吕玲, 孔俊. 一种基于运动目标的视频水印方法[J]. 计算机工程, 2013, 39(2): 155-159.
[7]	曹雏清, 李瑞峰, 赵立军. 基于深度图像技术的手势识别方法[J]. 计算机工程, 2012, 38(08): 16-18.
[8]	丁芒, 彭黎辉, 张煦, 刘强, 姚丹亚. 复杂交通场景中的运动目标提取方法[J]. 计算机工程, 2011, 37(7): 184-186.
[9]	李振华, 张兆杰, 徐胜男. 智能交通卡口监测系统的图像序列压缩编码[J]. 计算机工程, 2011, 37(22): 198-201.
[10]	王晓飞, 郭敏, 徐秋平. 基于图割与改进水平集的目标提取方法[J]. 计算机工程, 2010, 36(22): 214-216.
[11]	王春华;马国超;马苗. 基于目标提取的红外与可见光图像融合算法[J]. 计算机工程, 2010, 36(2): 197-200.

选择文件类型/文献管理软件名称

选择包含的内容