Deep Learning Algorithm for Person Re-Identification Based on Dual Network Architecture  

作　　者：Meng Zhu Xingyue Wang Honge Ren Abeer Hakeem Linda Mohaisen 

机构地区：[1]College of Information Engineering,Harbin University,Harbin,150086,China [2]Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software,Harbin University,Harbin,150086,China [3]College of Computer and Control Engineering,Northeast Forestry University,Harbin,150040,China [4]Heilongjiang Forestry Intelligent Equipment Engineering Research Center,Northeast Forestry University,Harbin,150040,China [5]Faculty of Computing and Information Technology,King Abdulaziz University,Jeddah,21589,Saudi Arabia

出　　处：《Computers, Materials & Continua》2025年第5期2889-2905,共17页计算机、材料和连续体(英文)

基　　金：supported by the Young Doctoral Research Initiation Fund Project of Harbin University“Research on Wood Recognition Methods Based on Deep Learning Fusion Model”(Project no.HUDF2022110);the Self-Funded Project of Harbin Science and Technology Plan“Research on Computer Vision Recognition Technology of Wood Species Based on Transfer Learning FusionModel”(Project no.ZC2022ZJ010027);the Fundamental Research Funds for the Central Universities(2572017PZ10).

摘　　要：Changing a person’s posture and low resolution are the key challenges for person re-identification(ReID)in various deep learning applications.In this paper,we introduce an innovative architecture using a dual attention network that includes an attentionmodule and a joint measurement module of spatial-temporal information.The proposed approach can be classified into two main tasks.Firstly,the spatial attention feature map is formed by aggregating features in the spatial dimension.Additionally,the same operation is carried out on the channel dimension to formchannel attention featuremaps.Therefore,the receptive field size is adjusted adaptively tomitigate the changing person posture issue.Secondly,we use a joint measurement method for the spatial-temporal information to fully harness the data,and it can also naturally integrate the information into the visual features of supervised ReID and hence overcome the low resolution problem.The experimental results indicate that our proposed algorithm markedly improves the accuracy in addressing changing human postures and low-resolution issues compared with contemporary leading techniques.The proposed method shows superior outcomes on widely recognized benchmarks,which are the Market-1501,MSMT17,and DukeMTMC-reID datasets.Furthermore,the proposed algorithmattains a Rank-1 accuracy of 97.4% and 94.9% mAP(mean Average Precision)on the Market-1501 dataset.Moreover,it achieves a 94.2% Rank-1 accuracy and 91.8% mAP on the DukeMTMC-reID dataset.

关 键 词：Person reidentification ReID computer vision self-attention spatial-temporal information 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]