An effective video shot boundary detection method based on supervised learning

Video shot boundary detection plays an every important role in video processing. It is the first step toward video content analysis and content-based video retrieval. We develop a novel approach for video shot boundary detection based on supervised learning. Our method consists in first extracting video frame feature using a supervised kernel non-locality preserving projections, then video frames are split into abrupt transitions, gradual transitions or normal frames using two cascaded Localized-SVM classifiers. Experimental results show the effectiveness of our method.