Shot detection with multi-measures

Many methods have been introduced to detect shot boundaries, e.g. pixel-by-pixel comparisons and histogram comparisons. But they ignore the problem of illumination variation inherent in the video production process especially in TV news reports. So they often can be confused when the incident illumination varies. The Color Ratio Histogram is proposed as frame content measure to solve the problem. However, it is computationally expensive. Different methods have both advantages and disadvantages, in this paper, the merits of different methods are associated to acquire a better performance. A good compromise between speed and accuracy is achieved. The detection is divided into two steps in which different metrics are used to identify different transitions. The effectiveness of our methods has been validated by experiments on some real-world video sequences