A solution to illumination variation problem in shot detection

Illumination variation problem is a crucial issue in the shot change detection because illumination change often induces a false shot boundary. In this paper, we present an efficient method that utilizes the edge direction histogram to reduce the false shot detection. A measure based on voting rule is defined to compute the similarities of the frame pairs. The experimental results show that our method achieves a high recall and precision with low computational complexity. The selection of two important thresholds is also discussed in detail.