The research of video matching algorithm based on spatio-temporal feature

The proliferation of video content makes video similarity detection an indispensable tool in video management, searching, and navigation. In this paper, an effective algorithm targets on detecting given video clips from TV programs is proposed. The algorithm has the following two advantages. Firstly, the algorithm can handle the offset of color or brightness and abrupt intense disturbance which are frequently seen on video transmission. Secondly, the algorithm is robust against TV channel noise and problems caused by video re-editing, such as the slow or fast motion. Video Spatio-Temporal Feature (VSTF) is defined to represent the content of this video. And an improved Dynamic Time Warping (DTW) algorithm is used to cope with noise and problems caused by video re-editing. Experimental results demonstrate the effectiveness of the algorithm.