多摄像机视场下基于一种DTN的多人脸实时跟踪系统  

Multi Face Real-Time Tracking System Based on DTN in Multi Camera Field of View

作　　者：任国印 吕晓琪[1,2,3] 李宇豪 Ren Guoyin;LüXiaoqi;Li Yuhao(School of Mechanical Engineering,Inner Mongolia University of Science&Technology,Baotou,Inner Mongolia 014010,China;School of Information Engineering,Inner Mongolia University of Science&Technology,Baotou,Inner Mongolia 014010,China;Inner Mongolia University of Technology,Hohhot,Inner Mongolia 010051,China)

机构地区：[1]内蒙古科技大学机械工程学院,内蒙古包头014010 [2]内蒙古科技大学信息工程学院,内蒙古包头014010 [3]内蒙古工业大学,内蒙古呼和浩特010051

出　　处：《激光与光电子学进展》2022年第2期111-121,共11页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61771266,81571753);包头市青年创新人才项目(0701011904)。

摘　　要：为了实现跨摄像机区域的多人脸图像跟踪,提出了一种基于双三分支孪生网络(DTN)的跨摄像机跟踪网络。具体方法是应用Chinese Whisper(CW)人脸聚类算法对同一行人的人脸图像进行聚类,并根据聚类结果通过智能监控确定捕获的目标人脸。通过改进FaceNet的网络结构和训练函数,实现了行人面部的精确跟踪。在LFW数据集上训练DTN后,通过边缘样本挖掘损失(MSML)和焦点损失难样本平衡训练,人脸识别率可以提高到99.51%。实验结果表明:通过比较同一视频监控场内人脸特征的相似性,所提网络可以通过该区域跟踪行人的人脸目标;通过摄像机间人脸特征的实时传输,实现了跨摄像机的人脸跟踪。In order to realize multi face image tracking across camera regions,a cross camera tracking network based on double three branch twin network(DTN)is proposed.The specific method is to apply Chinese Whisper(CW)face clustering algorithm to cluster the face images of the same pedestrian,and determine the captured target face through intelligent monitoring according to the results of face clustering.By improving the network structure and training function of FaceNet,pedestrian face tracking is realized accurately.After training DTN on LFW data set,the face recognition rate can be improved to 99.51%through margin sample mining loss(MSML)and focus loss difficult sample balance training.Experimental results show that by comparing the similarity of face features in the same video surveillance field,the proposed network can track pedestrian face targets through this area;through the real-time transmission of face features between cameras,cross camera face tracking is realized.

关 键 词：图像处理 人脸聚类 双三分支孪生网络 人脸跟踪 跨摄像机 人脸识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]