Algorithm of Shot Detection Based on SVM with Modified Kernel Function

Improving the precision of shot boundary detection is very important. This paper presents an algorithm for shot boundary detection based on SVM (support vector machine) in compressed domain. It uses the features, such as the type of macroblock, the difference between DC coefficients of two co-located blocks in successive frames and the type of frame, to segment a video into the shots by classifying the frames into three classes, namely, the frames of cut change, gradual change and non-change. In order to further improve the detection accuracy of shot boundary, we modify the kernel function of SVM based on its nature, and some experiments have been done to compare with other kernel functions commonly used. The experimental results show that the classifier with the kernel function of RBF + Gaussian RBF has the better classification performance and achieved higher recall and precision of shot detection.