A shot detection technique using linear regression of shot transition pattern

Abstract

Video segmentation acts as the fundamental step for various applications like, archiving, content based retrieval, copy detection and summarization of video data. Shot detection is first level of segmentation. In this work, a shot detection methodology is presented that evolves around a simple shot transition model based on the similarity of the frames with respect to a reference frame. Frames in an individual shot are very similar in terms of their visual content. Whenever a shot transition occurs a change in similarity values appears. For an abrupt transition, the rate of change is very high, while for gradual it is not so apparent. To overcome the effect of noise in similarity values, line is fit over a small window using a linear regression. Thus slope of this line exhibits the underlying pattern of transition. A novel algorithm for shot detection, hence, is developed based on the variation pattern of the similarity values of the frames with respect to a reference frame. First an algorithm is proposed, which is direct descendant of the underlying transition model and applies a threshold on the similarity values to detect the transitions. Then this algorithm is improved by utilizing the slope of linear approximation of variation in similarity values rather than the absolute values, following least square regression. Threshold on the slope is determined with a bias towards minimizing false rejection rate at the cost of false acceptance rate. Finally, a simple post-processing technique is adopted to reduce the false detection. Experiment is done with the video sequences taken from TRECVID 2001 database, action type movie video, recorded sports and news video. Comparison with few other systems indicates that the performance of the proposed scheme is quite satisfactory.