A Novel Video Copy Sub-sequence Detection and Location Method

Yuxiang Xie, Jie Yan, Xidao Luan, Lili Zhang, Yancheng Zhao, Yingmei Wei

Abstract: With the rapid growth of the internet and multimedia technology, there is an exponential growth of copy video, which causes some certain impact on video retrieval and copyright protection. Therefore, it becomes increasingly important to find copy videos and locate subsequent clips in a large-scale video database. In this paper, an efficient method is proposed to solve the current problem of video copy detection when the test video contains both copy video clips and non-copy video clips. This paper presents a method of judging the video copy sub-sequence based on the distance between the test video keyframe and the reference video keyframe. First, AlexNet is used to extract the features of the keyframe. Second, it judges whether each test video keyframe is a copy frame according to the distance. Then, the location of the copy sub-sequence is determined by finding the continuous copy frame, and then the video location of the copy sub-sequence is determined. Experimental results show that the proposed method can achieve 86.29% in recall and 95.71% in precision.