基于多尺度多粒度特征的行人重识别  

Multi-scale Multi-granularity Feature for Pedestrian Re-identification

作　　者：王栋[1] 周大可[1,2] 黄有达 杨欣[1] WANG Dong;ZHOU Da-ke;HUANG You-da;YANG Xin(School of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211100,China;Jiangsu Key Laboratory of Internet of Things and Control Technologies(Nanjing University of Aeronautics and Astronautics),Nanjing 211100,China)

机构地区：[1]南京航空航天大学自动化学院,南京211100 [2]江苏省物联网与控制技术重点实验室(南京航空航天大学),南京211100

出　　处：《计算机科学》2021年第7期238-244,共7页Computer Science

基　　金：国家自然科学基金(61573182)。

摘　　要：针对现有的基于卷积神经网络的行人重识别方法所提取的特征辨识力不足的问题,提出了一种基于多尺度多粒度特征的行人重识别方法。在训练阶段,该方法在卷积神经网络的不同尺度提取特征;然后对获得的多尺度特征图进行分块和池化,从而得到不同尺度的全局特征和局部特征的多粒度特征,使用不确定性权重调节Softmax损失和三元组损失来对特征向量进行监督训练。在推理阶段,对所获得的多尺度多粒度的特征进行融合,使用融合特征在图像库中进行相似度匹配。在Market-1501和DukeMTMC-ReID数据集上的实验表明,所提方法相比基准网络ResNet-50在Rank-1评价指标上分别提升了4.3%和3.6%,在mAP评价指标上分别提升了6.2%和6.6%。实验结果表明,所提方法能够增强提取特征的辨识力,提高行人重识别的性能。In order to address the problem of insufficient discriminative features for pedestrian re-identification extracted by exis-ting convolutional neural network,a novel multi-scale multi-granularity feature learning for pedestrian re-identification method is proposed.In the training phase,the method extracts multi-scale features at different stages of the convolutional neural network,and then blocks and pools these feature maps to obtain multi-granularity features containing global and local features,uses uncertainty to weight Softmax loss and triples loss and to supervise training process on feature vectors.In the inference phase,the obtained multi-scale multi-granularity features are concatenated,and finally the concatenated features are used to perform similarity matching in the gallery.Experiments on the Market-1501 and DukeMTMC-ReID datasets show that the proposed method improves the Rank-1 evaluation index by 4.3%and 3.6%,respectively,compared with the benchmark network ResNet-50,and improves the mAP evaluation index respectively 6.2%and 6.6%.The results show that the proposed method can enhance the discrimination of extracted features and improve the performance of pedestrian re-identification.

关 键 词：机器视觉 卷积神经网络 行人重识别 多尺度特征 多粒度特征 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]