计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230300236-6.doi: 10.11896/jsjkx.230300236

• 图像处理&多媒体技术 • 上一篇    下一篇

基于多尺度局部特征融合的行人重识别方法

吴蕾, 王海瑞, 朱贵富, 赵江河   

  1. 昆明理工大学信息工程与自动化学院 昆明 650500
  • 发布日期:2024-06-06
  • 通讯作者: 王海瑞(hrwang88@163.com)
  • 作者简介:(836863390@qq.com)
  • 基金资助:
    国家自然科学基金(61863016,61263023)

Person Re-identification Method Based on Multi-scale Local Feature Fusion

WU Lei, WANG Hairui, ZHU Guifu, ZHAO Jianghe   

  1. Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China
  • Published:2024-06-06
  • About author:WU Lei,born in 1996,postgraduate.Her main research interests include computer vision and person re-identification.
    WANG Hairui,born in 1969,Ph.D,professor,Ph.D supervisor.His main research interests include multimedia intelligent technology,embedded application technology,etc.
  • Supported by:
    National Natural Science Foundation of China(61863016,61263023).

PDF (PC)

294

摘要： 针对现有行人重识别方法在提取行人特征时存在特征不对齐、忽略相邻区域语义相关性、背景杂乱以及训练效率低的问题,提出一种多尺度局部特征融合的方法。首先引入空间变换网络对图像进行自适应仿射变换,实现行人空间特征对齐;接着横向均等分割不同尺度的特征图,对相邻局部块采取不同的拼接方式,以弥补切割造成的相邻块关联性信息缺失的问题;再融合全局特征与局部特征,挖掘二者之间的关联性。同时,融入随机擦除的方法对数据集进行处理,防止模型过拟合;并且使用多种损失函数对网络模型进行训练,提升模型的类内紧致性和类间差异性。将所提方法在Market-1501和DukeMTMC-ReID数据集上进行实验,Rank-1分别达到95.0%,88.8%,mAP分别达到89.2%,78.9%,结果表明所提方法能够提取更具判别力的行人特征。

关键词: 行人重识别, 局部特征, 特征空间分割, 空间变换网络, 随机擦除

Abstract: Aiming at the problems of feature misalignment,ignoring semantic correlation between adjacent regions,background clutter and low training efficiency when extracting pedestrian features in existing person re-identification methods,a multi-scale local feature fusion method is proposed.Firstly,the spatial transformation network is introduced to perform adaptive affine transformation on the image to realize the alignment of pedestrian spatial features.Secondly,the feature maps of different scales are segmented horizontally,and the adjacent local blocks are spliced in different ways to make up for the lack of correlation information of adjacent blocks caused by cutting.Then,the correlation between global features and local features is mined.At the same time,the random erasure method is incorporated to process the data set to prevent the model from overfitting.And a variety of loss functions are used to train the network model to improve the intra-class compactness and inter-class diversity of the model.Finally,experiments are carried out on Market-1501 and DukeMTMC-ReID datasets,the Rank-1 reaches 95.0% and 88.8%,and the mAP reaches 89.2% and 78.9%,respectively.The results show that the proposed method can extract more discriminative pedestrian features.

Key words: Person re-identification, Local feature, Feature space segmentation, Spatial transformation network, Random erasure

中图分类号: 

  • TP391
[1]MING Z,ZHU M,WANG X,et al.Deep learning-based person re-identification methods:A survey and outlook of recent works[J].Image and Vision Computing,2022,119:104394.
[2]YAO Z,GONG X,CHEN R,et al.Research progress,challenge and prospect of local features for person re-identification[J].Acta Automatica Sinica,2021,47(12):2742-2760.
[3]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.2017:1077-1085.
[4]MIAO J,WU Y,LIU P,et al.Pose-guided feature alignment for occluded person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:542-551.
[5]LIU J,NI B,YAN Y,et al.Pose transferrable person re-identifi-cation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:4099-4108.
[6]PANG Y X,ZHANG H X,ZHU L,et al.Feature generation based on relation learning and image partition for occluded person re-identification[J].Journal of Visual Communication and Image Representation,2023,91.
[7]SUN Y,ZHENG L,YANG Y,et al.Beyond part models:Person retrieval with refined part pooling(and a strong convolutional baseline)[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:480-496.
[8]WANG G,YUAN Y,CHEN X,et al.Learning discriminativefeatures with multiple granularities for person re-identification[C]//Proceedings of the 26th ACM International Conference on Multimedia.2018:274-282.
[9]FU Y,WEI Y,WANG G,et al.Self-similarity grouping:A simple unsupervised cross domain adaptation approach for person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:6112-6121.
[10]ZHENG F,DENG C,SUN X,et al.Pyramidal person re-identification via multi-loss dynamic training[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:8514-8522.
[11]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Utah,USA:IEEE,2018:7132-7141.
[12]CAI H,WANG Z,CHENG J.Multi-scale body-part maskguided attention for person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.2019.
[13]LI W,ZHU X,GONG S.Harmonious attention network for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:2285-2294.
[14]CHEN T,DING S,XIE J,et al.ABD-Net:Attentive but Diverse Person Re-Identification[J].arXiv:2019.00844,2019.
[15]ZHANG G Q ,LIN W S,CHANDRAN A K,et al.Complementary networks for person re-identification[J]Information Sciences,2023,633.
[16]MENG Y B,MU S R,LIU G H,et al.Person re-identification method based on GoogLeNet-GMP based on vector Attention mechanism[J].Computer Science,2022,49(7):142-147.
[17]JADERBERG M,SIMONYAN K,ZISSERMAN A.Spatialtransformer networks[C]//Advances in Neural Information Processing Systems.2015:2017-2025.
[18]LIU L,LI X,LEI X M.A Person Re-Identification Method with Multi-Scale and Multi-Feature Fusion[J].Journal of Computer-Aided Design & Computer Graphics,2022,34(12):1868-1876.
[19]LUO H,JIANG W,ZHANG X,et al.Alignedreid+ +:Dynamic-ally matching local information for person re-identification[J].Pattern Recognition,2019,94:53-61.
[20]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.
[21]ZHANG W F,HUANG L,WEI Z Q,et al.Appearance feature enhancement for person re-identification[J].Expert Systems with Applications,2021,163:113771.
[22]ZHOU K Y,YANG Y X,CAVALLARO A,et al.Omni-scale feature learning for person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Los Alamitos:IEEE Computer Society Press,2019:3701-3711.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发