基于注意力机制与局部关联特征的行人重识别北大核心CSCD

由于行人在真实场景下易受到背景、遮挡、姿态等问题的影响,为获取行人图像中更具辨别能力的特征,提出一种基于注意力机制和局部关联特征的行人重识别方法。首先,在网络框架中嵌入注意力模块以关注图像中表达能力强的特征;然后,利用图像中相邻区域的关联得到局部关联特征,并结合全局特征。本文方法在Market1501和DukeMTMC-ReID数据集上进行实验,Rank-1指标分别达到了95.3%和90.1%。结果证明,本文方法能充分获取判别力强的特征信息,使模型具有较强的识别能力。

Person re-identification based on attention mechanism and local association feature

Because pedestrians are easily affected by background,occlusion,postu re and other issues in real scenes,in order to obtain more discriminative features in pedestrian ima ges,a person re-identification method based on attention mechanism and local association fea ture is proposed. Firstly,the attention module is embedded in the network framework to pay attent ion to the features with strong expressive ability in the image.Then,the local association features are obtained by using the association of adjacent parts in the image,and combined with the global feat ures.The experiments on Market1501 and DukeMTMC-ReID datasets show that the Rank-1 inde x reaches 95.3%and 90.1%,respectively.The results show that the proposed method can full y obtain the feature information with strong discrimination and make the model have strong re cognition ability.