Video Shot Boundary Recognition Based on Adaptive Locality Preserving Projections

Abstract

A novel video shot boundary recognition method is proposed, which includes two stages of video feature extraction and shot boundary recognition. Firstly, we use adaptive locality preserving projections (ALPP) to extract video feature. Unlike locality preserving projections, we define the discriminating similarity with mode prior probabilities and adaptive neighborhood selection strategy which make ALPP more suitable to preserve the local structure and label information of the original data. Secondly, we use an optimized multiple kernel support vector machine to classify video frames into boundary and nonboundary frames, in which the weights of different types of kernels are optimized with an ant colony optimization method. Experimental results show the effectiveness of our method.

A Comparison of Corner Feature Detectors for Video Abrupt Shot Detection

“…Researchers have attempted to detect the abrupt shot boundaries by focusing on visual interruptions between frames that can be detected by searching for two successive frames that are totally uncorrelated. Various useful features extracted from the video frames are used to distinguish between transition and nontransition frames by applying similarity measures that are then compared to threshold [6].…”