基于孪生网络和重排序的行人重识别  

Person re-identification based on siamese network and reranking

作　　者：陈首兵 王洪元[1] 金翠 张玮[2] CHEN Shoubing;WANG Hongyuan;JIN Cui;ZHANG Wei(College of Information Science and Engineering,Changzhou University,Changzhou Jiangsu 213164,China;Institute of Electronic and Electrical,Changzhou College of Information Technology,Changzhou Jiangsu 213164,China)

机构地区：[1]常州大学信息科学与工程学院,江苏常州213164 [2]常州信息职业技术学院电子与电气工程学院,江苏常州213164

出　　处：《计算机应用》2018年第11期3161-3166,共6页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61572085)~~

摘　　要：针对非重叠多摄像头下的行人重识别(Re-ID)易受到光照、姿势及遮挡等影响和实验过程中存在图像错误匹配的情况,提出一种基于孪生网络和重排序的行人重识别方法。首先,给定一对行人训练图像,孪生网络可以同时学习一个具有辨别力的卷积神经网络(CNN)特征和相似性度量,并预测两个输入图像的行人身份以及判断它们是否属于同一个行人;然后,通过k互近邻方法来降低图像错误匹配的情况;最后,将欧氏距离和杰卡德距离加权来对排序表进行重排序。在数据集Market1501和CUHK03上进行多次实验,实验结果显示在Market1501上Single Query情况下在图库中第一次就成功匹配的概率(Rank1)达到83.44%,平均精度均值(mAP)为68.75%,在CUHK03上singleshot情况下Rank1达到85.56%,mAP为88.32%,明显高于传统的基于特征表示和度量学习的方法。Person Re-Identification(Re-ID)under non-overlapping multi-camera is easily affected by illumination,posture,and occlusion,and there are image mismatches in the experimental process.A Re-ID method based on siamese network and reranking was proposed.Firstly,a pair of pedestrian training images were given,a discriminative Convolutional Neural Network(CNN)feature and similarity measure could be simultaneously learned by the siamese network to predict the pedestrian identity of the two input images and determine whether they belonged to the same pedestrian.Then,the k-reciprocal neighbor method was used to reduce the image mismatches.Finally,Euclidean distance and Jaccard distance were weighted to rerank the sorted list.Several experiments were performed on the datasets Market1501 and CUHK03.The experimental results show that the Rank1(the probability of matching successfully for the first time)reaches 83.44%and mAP(mean Average Precision)is 68.75%under Single Query on Market1501.In the case of single-shot on CUHK03,the Rank1 reaches 85.56%and mAP is 88.32%,which are significantly higher than those of the traditional methods based on feature representation and metric learning.

关 键 词：行人重识别 孪生网络 k互近邻 杰卡德距离 重排序 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]