With the rapid development of multimedia communications and the computer network technology, video information has a rising proportion in multimedia information. It owns the great amount of data so that it can obtain accurate information for needed video retrieval research, which has become one of the hot topics of research in this field. By taking soccer video for example, this paper firstly analyzes structure of the soccer video and framework structure. Based on this, this paper makes a specific analysis on the extraction of soccer video feature by combining with the literature to apply SSD apparent characteristic. And then, assisted by the improvement of Hidden Markov Model (HMM), this paper constructs the second frame differential method to detect the shot of soccer video. The test results show that the precision of this method is higher in close-up and misjudgment slow motion. However, it has certain leak detection in slow motion replay of high speed movement.
An Effective Slow-Motion Detection Approach for Compressed Soccer Videos