Scene Change Detection for H.264 Using Dynamic Threshold Techniques

Several scene-change detection algorithms have been proposed in literature up to now. Most of them use fixed thresholds for the similarity metrics used to decide if there was a change or not. These thresholds are obtained by empirically or they must be calculated before the detection after the whole sequence is obtained. Performance of most scene change detectors decreases considerably for videos with high scene complexity and variation. In this paper, we review previous works in this area, and study the correlation between local statistical characteristics, scene duration and scene change. Based on this analysis, we further propose and implement a novel scene change detection method for H.264 codec, defining an automated, dynamic threshold model which can efficiently trace scene changes. Experimental results on QCIF videos indicate very good performance with significantly improved accuracy combined with minimum complexity.