计算机科学 ›› 2021, Vol. 48 ›› Issue (10): 204-211.doi: 10.11896/jsjkx.210300128

• 计算机图形学&多媒体 • 上一篇    下一篇

多方向分区网络结构的行人再识别

唐一星, 刘学亮, 胡社教   

  1. 合肥工业大学计算机与信息学院 合肥230031
  • 收稿日期:2021-03-12 修回日期:2021-05-26 出版日期:2021-10-15 发布日期:2021-10-18
  • 通讯作者: 刘学亮(Liuxueliang1982@gmail.com)
  • 作者简介:elsa_kf2016@163.com
  • 基金资助:
    科技部重点研发计划(2018AAA0102002);国家自然科学基金(61932009,61632007,61976076)

Multi-orientation Partitioned Network for Person Re-identification

TANG Yi-xing, LIU Xue-liang, HU She-jiao   

  1. School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230031,China
  • Received:2021-03-12 Revised:2021-05-26 Online:2021-10-15 Published:2021-10-18
  • About author:TANG Yi-xing,born in 1995,postgra-duate.Her main research interests include computer vision and so on.
    LIU Xue-liang,born in 1981,Ph.D,professor,is a member of China Computer Federation.His main research interests include computer vision and multimedia information retrieval.
  • Supported by:
    National Key R&D Program of China(2018AAA0102002) and National Natural Science Foundation of China(61932009,61632007,61976076).

摘要: 将全局特征与局部特征相结合是提高行人再识别(re-identification)任务识别能力的重要解决方案。以往主要借助姿态估计等外部信息来定位有相应语义的区域,从而挖掘局部信息,这种方法大多是非端到端的,训练过程复杂且缺乏鲁棒性。针对该问题,文中提出了一种能有效挖掘局部信息并且能结合全局信息与局部信息进行端到端特征学习的方法,即多方向分区网络(Multi-orientation Partitioned Network,MOPN),该网络有3个分支,一个用于提取全局特征,两个用于提取局部特征。该算法不依靠外部信息,而是在不同的局部分支分别将图像按水平方向和竖直方向切分为若干横条纹和竖条纹,从而得到不同的局部特征表示。在Market-1501、DukeMTMC-reID、CUHK03和跨模态素描数据集SketchRe-ID上的综合实验表明,该算法的整体性能优于其他对比算法,具备有效性和鲁棒性。

关键词: 多分支网络, 局部特征, 全局特征, 深度学习, 行人再识别

Abstract: Combining global features with local features is an important solution to improve discriminative performances in person re-identification (Re-ID) task.In the past,external information was used to locate regions with corresponding semantics,thus mining local information.Most of these methods are not end-to-end,so the training process is complex.To solve this problem,a multi-orientation partitioned network (MOPN) is proposed,which can effectively mine local information and combine global information with local information for end-to-end feature learning.The network has three branches:one for extracting global feature and two for mining local information.Without relying on external information,the algorithm divides pedestrians' images into hori-zontal and vertical stripes in different local branches respectively,so as to obtain different local feature representations.Plenty of experiments conducted on Market-1501,DukeMTMC-reID,CUHK03 and cross-modal dataset SketchRe-ID show that the proposed method has better overall performance than other comparison algorithms,and is effective and robust.

Key words: Deep learning, Global feature, Local feature, Multi-branch network, Person Re-identification

中图分类号: 

  • TP391
[1]LI H,TANG M,LIN J W,et al.Cross-modality Person Re-identification Framework Based on Improved Hard Triplet Loss [J].Computer Science,2020,47(10):180-186.
[2]YI D,LEI Z,LIAO S,et al.Deep metric learning for personreidentification[C]//2014 22nd International Conference on Pattern Recognition.Piscataway:IEEE Press,2014:34-39.
[3]LI W,ZHAO R,XIAO T,et al.Deepreid:Deep filter pairingneural network for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2014:152-159.
[4]ZHENG L,YANG Y,HAUPTMANN A G.Person re-identification:Past,present and future [J].arXiv:1610.02984,2016.
[5]SUN Y,ZHENG L,YANG Y,et al.Beyond part models:Person retrieval with refined part pooling (and a strong convolutional baseline) [C]//European Conference on Computer Vision.Berlin:Springer Press,2018:480-496.
[6]LI S S,LIU X L,ZHAO Y,et al.Person re-identification based on multi-scale constraint network [J].Pattern Recognition Letters,2020,138:403-409.
[7]WANG G,YUAN Y,CHEN X,et al.Learning discriminative features with multiple granularities for person re-identification[C]//Proceedings of the 26th ACM International Conference on Multimedia.New York:ACM Press,2018:274-282.
[8]ZHENG L,HUANG Y,LU H,et al.Pose-invariant embedding for deep person re-identification [J].IEEE Transactions onImage Processing,2019,28(9):4500-4509.
[9]WEI L,ZHANG S,YAO H,et al.Glad:Global-local-alignment descriptor for pedestrian retrieval[C]//Proceedings of the 25th ACM International Conference on Multimedia.New York:ACM Press,2017:420-428.
[10]ZHAO H,TIAN M,SUN S,et al.Spindle net:Person re-identification with human body region guided feature decomposition and fusion[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2017:1077-1085.
[11]CHEN L Y,LI W J.Multishape part network architecture for person re-identification [J].Journal of Image and Graphics,2019,24(11):1932-1941.
[12]XIAO T,LI H,OUYANG W,et al.Learning deep feature representations with domain guided dropout for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2016:1249-1258.
[13]WU S,CHEN Y C,LI X,et al.An enhanced deep feature representation for person re-identification[C]//2016 IEEE Winter Conference on Applications of Computer Vision.Piscataway:IEEE Press,2016:1-8.
[14]YAO H,ZHANG S,HONG R,et al.Deep representation lear-ning with part loss for person re-identification [J].IEEE Tran-sactions on Image Processing,2019,28(6):2860-2871.
[15]SU C,ZHANG S,XING J,et al.Deep attributes driven multi-camera person re-identification[C]//European Conference on Computer Vision.Berlin:Springer Press,2016:475-491.
[16]SU C,LI J,ZHANG S,et al.Pose-driven deep convolutionalmodel for person re-identification[C]//Proceedings of the IEEE International Conference on Computer Vision.Piscataway:IEEE Press,2017:3960-3969.
[17]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2016:770-778.
[18]SONG G,LENG B,LIU Y,et al.Region-based quality estimation network for large-scale person re-identification[C]//Proceedings of Association for the Advancement of Artificial Intelligence.Menlo Park:AAAI,2018:7347-7354.
[19]HERMANS A,BEYER L,LEIBE B.In defense of the tripletloss for person re-identification [J].arXiv:1703.07737,2017.
[20]LIU W,ANGUELOV D,ERHAN D,et al.Ssd:Single shotmultibox detector[C]//European Conference on Computer Vision.Berlin:Springer Press,2016:21-37.
[21]ZHENG L,SHEN L,TIAN L,et al.Scalable person re-identification:A benchmark[C]//Proceedings of the IEEE Internatio-nal Conference on Computer Vision.Piscataway:IEEE Press,2015:1116-1124.
[22]ZHENG Z,ZHENG L,YANG Y.Unlabeled samples generated by gan improve the person re-identification baseline in vitro[C]//Proceedings of the IEEE International Conference on Computer Vision.Piscataway:IEEE Press,2017:3754-3762.
[23]PANG L,WANG Y,SONG Y Z,et al.Cross-domain adversarial feature learning for sketch re-identification[C]//Proceedings of the 26th ACM International Conference on Multimedia.New York:ACM,2018:609-617.
[24]CHEN Y,ZHU X,GONG S.Person re-identification by deep learning multi-scale representations[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops.Piscataway:IEEE Press,2017:2590-2600.
[25]LI W,ZHU X,GONG S.Person re-identification by deep joint learning of multi-loss classification[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence.San Francisco:Morgan Kaufmann,2017:2194-2200.
[26]SI J,ZHANG H,LI C G,et al.Dual attention matching network for context-aware feature sequence based person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2018:5363-5372.
[27]ZHANG Y,XIANG T,HOSPEDALES T M,et al.Deep mutual learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2018:4320-4328.
[28]ZHENG Z,ZHENG L,YANG Y.Pedestrian alignment network for large-scale person re-identification [J].IEEE Transactions on Circuits and Systems for Video Technology,2018,29(10):3037-3045.
[29]SUN Y,ZHENG L,DENG W,et al.Svdnet for pedestrian retrieval[C]//Proceedings of the IEEE International Conference on Computer Vision.Piscataway:IEEE Press,2017:3800-3808.
[30]BARBOSA I B,CRISTANI M,CAPUTO B,et al.Looking beyond appearances:Synthetic training data for deep cnns in reidentification[J].Computer Vision and Image Understanding,2018,167:50-62.
[31]WANG C,ZHANG Q,HUANG C,et al.Mancs:A multi-task attentional network with curriculum sampling for person reidentification[C]//Proceedings of the European Conference on Computer Vision.Berlin:Springer Press,2018:365-381.
[32]SHEN Y,LI H,XIAO T,et al.Deep group-shuffling randomwalk for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscata-way:IEEE Press,2018:2265-2274.
[33]MATSUKAWA T,OKABE T,SUZUKI E,et al.Hierarchical gaussian descriptor for person re-identification[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2016:1363-1372.
[34]USTINOVA E,GANIN Y,LEMPITSKY V.Multi-region bili-near convolutional neural networks for person re-identification[C]//2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance.Piscataway:IEEE Press,2017:1-6.
[35]WU L,SHEN C,HENGEL A.Personnet:Person re-identifica-tion with deep convolutional neural networks [J].Computer Vision and Image Understanding,2018,167:63-73.
[36]ZHANG L,XIANG T,GONG S.Learning a discriminative null space for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Pisca-taway:IEEE Press,2016:1239-1248.
[37]PAISITKRIANGKRAI S,SHEN C,VAN DEN HENGEL A.Learning to rank in person re-identification with metric en- sembles[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2015:1846-1855.
[38]VARIOR R R,HALOI M,WANG G.Gated siamese convolutional neural network architecture for human re-identification[C]//European Conference on Computer Vision.Berlin:Sprin-ger Press,2016:791-808.
[39]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2015:1-9.
[40]GUI S,ZHU Y,QIN X,et al.Learning Multi-level Domain Invariant Features for Sketch Re-identification[J].Neurocompu-ting,2020,403:294-303.
[41]SANGKLOY P,BURNELL N,HAM C,et al.The sketchy database:learning to retrieve badly drawn bunnies [J].ACM Transactions on Graphics,2016,35(4):1-12.
[42]YU Q,LIU F,SONG Y Z,et al.Sketch me that shoe[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016.Piscataway:IEEE Press,2016:799-807.
[1] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[2] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[3] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[4] 李宗民, 张玉鹏, 刘玉杰, 李华.
基于可变形图卷积的点云表征学习
Deformable Graph Convolutional Networks Based Point Cloud Representation Learning
计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[5] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[6] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[7] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[8] 陈坤峰, 潘志松, 王家宝, 施蕾, 张锦.
基于双目叠加仿生的微换衣行人再识别
Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation
计算机科学, 2022, 49(8): 165-171. https://doi.org/10.11896/jsjkx.210600140
[9] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[10] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[11] 程成, 降爱莲.
基于多路径特征提取的实时语义分割方法
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[12] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[13] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[14] 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫.
小样本雷达辐射源识别的深度学习方法综述
Survey of Deep Learning for Radar Emitter Identification Based on Small Sample
计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[15] 祝文韬, 兰先超, 罗唤霖, 岳彬, 汪洋.
改进Faster R-CNN的光学遥感飞机目标检测
Remote Sensing Aircraft Target Detection Based on Improved Faster R-CNN
计算机科学, 2022, 49(6A): 378-383. https://doi.org/10.11896/jsjkx.210300121
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!