一种融合全局人脸—行人特征的在线跨镜多目标跟踪方法OA

To address the problem of limited single-camera views and insufficient feature fusion of tar-get tracking,an online multi-target multi-camera tracking method with global face-pedestrian feature fu-sion is proposed.Firstly,by constructing a global face-pedestrian feature pool and adopting a global long-term identity management mechanism,real-time multi-camera information fusion and identity as-sociation are realized during single-camera tracking.Secondly,multi-category feature extraction and adaptive threshold adjustment are integrated,and a spatio-temporal-appearance joint constraint model is introduced to enhance the accuracy and robustness of multi-camera correlation.Finally,in order to verify the method,a multi-camera pedestrian tracking dataset covering different complexities is con-structed.Experimental results show that compared with those of the comparison methods,the average number of ID switches(IDS)is reduced by more than 20 times,and the maximum number of ID F1 score(IDF1)is increased by about 30%.In the multi-camera tracking task,IDS in the multi-pedestrian scene is reduced from 132 to 126.Ablation experiments confirm the effectiveness of each module of the pro-posed method,and the real-time test shows that frames per second(FPS)of this method can reach 25.15.