基于匹配链的视频行人目标检测

Pedestrian Detection Based on Matching Chain in Video

在视频行人目标检测中,利用视频中前后帧检测结果之间的相似性,建立前后帧检测结果之间的匹配链,依靠同一条匹配链中所有的检测结果,优化当前帧检测的结果,提高检测精度。实验结果显示,相比于其他所测试的行人检测方法,论文提出的协同框架能够有效提高行人检测的性能。

When detecting pedestrians in video,a matching chain that connects the detected results of sequential frames is constructed through the similarity of the detected results. Relying on the detected results on the same chain,the result of the frames detecting now is optimized,and the accuracy of detection is also promoted. Experimental results show that the proposed method can effectively promote the performance of the proposed framework compared with the tested other methods.