基于统计模型的镜头突变检测方法

Abrupt Shot Change Detection Based on Statistical Model

提出了一种基于统计模型的镜头突变检测方法。首先分析了现有方法的优缺点;其次选取了具有运动补偿功能的特征,来度量视频帧之间的内容变化;然后对镜头突变检测过程进行了统计建模,将镜头突变检测转化为使建立的统计模型的错误率最小;最后对闪光灯造成的亮度变化进行了单独处理。实验表明,该方法对于镜头运动、物体运动以及闪光灯的处理具有较好的鲁棒性,并具有很好的镜头突变检测效果。

In this article an abrupt shot change detection method based on statistical model is proposed. First, we analyze the classical methods and identify the major issues in shot boundary detection. Second, we chose a feature with motion compensation for the visual content discontinuities. Third, we model the shot boundary detection process with an appropriate statistical function. Finally, we processed the sharp brightness changes caused by flash lights. In the experiments, this method is robust in processing camera motion, object motion and treating flash light. Compared with the adaptive threshold of histogram method, this method decreases the false detection rate and missed detection rate and also show a good detection result.