Shot Boundary Detection in Soccer Video using Twin-comparison Algorithm and Dominant Color Region

Abstract

The first step in generic video processing is temporal segmentation, i.e. shot boundary detection. Camera shot transitions can be either abrupt (e.g. cuts) or gradual (e.g. fades, dissolves, wipes). Sports video is one of the most challenging domains for robust shot boundary detection. We proposed a shot boundary detection algorithm for soccer video based on the twin-comparison method and the absolute difference between frames in their ratios of dominant colored pixels to total number of pixels. With this approach the detection of gradual transitions is improved by decreasing the number of false positives caused by some camera operations. We also compared performances of our algorithm and the standard twin-comparison method.