Dynamic Threshold and Fast Motion Estimation Algorithm based on PSO for H. 264's Scene Change Detection

Many scene change detection algorithms proposed so far use fixed thresholds for identifying the scene change. These thresholds are obtained empirically or they must be calculated before the detection once the whole sequence is obtained. For videos having high scene complexity and variation, the performance of most of the scene change algorithms decrease considerably. In this paper, we study the correlation between local statistical characteristics, scene duration and scene change. Based on this analysis, we further propose and implement a scene change algorithm for H.264 codec, defining an automated, dynamic threshold model with fast motion estimation algorithm having low complexity which can efficiently trace out scene changes. Experimental results on QCIF videos indicate very good performance with significantly improved accuracy combined with minimum complexity.