[1]詹敏,王佳斌,邹小波.应用空间约束和二次相似度学习算法的行人再识别[J].华侨大学学报(自然科学版),2019,40(3):384-389.[doi:10.11830/ISSN.1000-5013.201707021]
 ZHAN Min,WANG Jiabin,ZOU Xiaobo.Pedestrian Re-Identification Using Spatial Constraint and Quadratic Similarity Learning Algorithm[J].Journal of Huaqiao University(Natural Science),2019,40(3):384-389.[doi:10.11830/ISSN.1000-5013.201707021]
点击复制

应用空间约束和二次相似度学习算法的行人再识别()
分享到:

《华侨大学学报(自然科学版)》[ISSN:1000-5013/CN:35-1079/N]

卷:
第40卷
期数:
2019年第3期
页码:
384-389
栏目:
出版日期:
2019-05-20

文章信息/Info

Title:
Pedestrian Re-Identification Using Spatial Constraint and Quadratic Similarity Learning Algorithm
文章编号:
1000-5013(2019)03-0384-06
作者:
詹敏 王佳斌 邹小波
华侨大学 工学院, 福建 泉州 362021
Author(s):
ZHAN Min WANG Jiabin ZOU Xiaobo
College of Technology, Huaqiao University, Quanzhou 362021, China
关键词:
行人再识别 空间约束 二次相似度函数 多项式特征图
Keywords:
pedestrian re-identification spatial constraints quadratic similarity function polynomial feature graph
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.201707021
文献标志码:
A
摘要:
针对空间分布的全局外观潜在变化的行人再识别问题,提出一种基于空间约束和二次相似度学习算法.通过二次相似度函数(QSF)估计每个子区域的相似度,从而形成多项式特征图,并将所有特征图融合到统一的框架中.该框架利用局部相似度和全局相似度的互补优势,结合多个视觉线索进一步提高算法的鲁棒性.实验对比3个公共数据集,结果表明:基于空间约束和二次相似度学习算法具有显著的识别性能.
Abstract:
According to the pedestrian re-identification problem with potential changes in global appearance of spatial distribution, a learning algorithm based on a spatial constraint and quadratic similarity is proposed. The similarity of each sub-region is estimated by the quadratic similarity function(QSF)and the polynomial feature graph is formed and all the feature graphs are merged into a uniformed framework. The framework utilizes the complementary advantages of local similarity and global similarity to flexibly combine multiple visual cues to further improve the robustness of the algorithm. Compared with the experimental results of the three public data sets, the identification performance of proposed method is significantly improved compared with the existing pedestrian re-identification method.

参考文献/References:

[1] FARENZENA M,BAZZANI L,PERINA A,et al.Person re-identification by symmetry-driven accumulation of local features[C]//Computer Vision and Pattern Recognition.San Francisco: IEEE Press,2010:2360-2367.
[2] DONG S C,CRISTANI M,STOPPA M,et al.Custom pictorial structures for re-identification[C]// British Machine Vision Conference.British:[s.n.],2011:1-11.
[3] MA B,SU Y,JURIE F.BiCov: A novel image representation for person re-identification and face verification[C]//British Machive Vision Conference.Guildford:[s.n.],2012:1-11.
[4] HIRRER M,ROTH P M,STINGER M,et al.Relaxed pairwise learned metric for person re-identification[C]//European Conference on Computer Vision.Florence:Springer-Verlag,2012:780-793.
[5] JÉGOU H,CHUM O.Negative evidences and co-occurences in image retrieval: The benefit of PCA and whitening[C]//European Conference on Computer Vision.Florence:Springer-Verlag,2012:774-787.
[6] LI Zhen,CHANG Shiyu,LIANG Feng,et al.Learning locally-adaptive decision functions for person verification[J].2013,9(4):3610-3617.
[7] ZHENG Weishi,GONG Shaogang,XIANG Tao.Reidentification by relative distance comparison[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(3):653-668.DOI:10.1109/TPAMI.2012.138
[8] 杜宇宁,艾海舟.基于二次相似度函数学习的行人再识别[J].计算机学报,2016,39(8):1639-1651.DOI:10.11897/SP.J.1016.2016.01639.
[9] CHEN Dapeng,YUAN Zejian,HUA Gang,et al.Similarity learning on an explicit polynomial kernel feature map for person re-identification[C]//Conference on Computer Vision and Pattern Recognition.Boston:IEEE press,2015:1565-1573.
[10] 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 of Tracking and Surveillance.Rio de Janeiro:IEEE press,2007:41-47.
[11] CHEN C.L,LIU Chunxiao,GONG Shaogang.Person re-identification by manifold ranking[C]//IEEE International Conference on Image Processing.Melbourne:IEEE Press,2014:3567-3571.
[12] ZHENG Liang,SHEN Liyue,TIAN LU,et al.Scalable person re-identification: A benchmark[C]//Proceedings-2015 IEEE International Conference on Computer Vision.Santiago:Institute of Electrical and Electronics Engineers Inc,2015:1116-1124.DOI:10.1109/ICCV.2015.133.
[13] 张国亮,王展妮,王田.应用计算机视觉的动态手势识别综述[J].华侨大学学报(自然科学版),2014,35(6):653-658.DOI:10.11830/ISSN.1000-5013.2014.06.0653.
[14] PAISITKRIANGKRAI S,SHEN Chunhua,HENGEL A V D.Learning to rank in person re-identification with metric ensembles[J].Computer Science,2015:1846-1855.DOI:10.1109/CVPR.2015.7298794.
[15] XIONG Fei,GOU Mengran,CAMPS O,et al.Person re-identification using kernel-based metric learning methods[C]//European Conference on Computer Vision.Boston:Springer,2014:1-16.

备注/Memo

备注/Memo:
收稿日期: 2017-07-05
通信作者: 王佳斌(1974-),男,副教授,博士,主要从事物联网技术、大数据、云计算等研究.E-mail:fatwang@hqu.edu.cn.
基金项目: 国家自然科学青年科学基金资助项目(61505059); 福建省厦门市科技局产学院科技创新项目(3502Z20173046); 华侨大学研究生科研创新能力培育计划项目(1511422006)
更新日期/Last Update: 2019-05-20