Video Shot segmentation algorithm based on SURF

Video Shot segmentation is the key technology in content-based video retrieval and browsing, and which will directly affect the results of video retrieval. In view of the problems that the traditional shot segmentation algorithm is complex, the feature of video frame is not ideal, and the segmentation accuracy is low, this paper proposes a shot segmentation algorithm based on SURF (Speeded up Robust Features). This algorithm obtains the boundary of shots by computing the SURF features of video frames and calculating the feature matching rate. The experimental results show that: this algorithm can greatly reduce the amount of computation and data, improve the efficiency of the algorithm. And this algorithm has a great improvement in the accuracy of shot segmentation compared with shot segmentation algorithm based on color histogram.