A Method of Shot-Boundary Detection Based on HSV Space

Abstract

Shot-Boundary detection is a critical step in video retrieval system. The accuracy of Shot-Boundary detection directly affects the retrieval system performance. There are many shot boundary detection algorithms, such as pixel-based algorithms and histogram-based algorithms, etc. However, these shot boundary detection algorithms are not good at detecting motion shot. This paper proposes an adaptive shot boundary detection algorithm based on HSV space. Comparing with existing pixel-based algorithms, our algorithm consider the characteristics of two shot transitions and uses different data processing in cut and gradual transition detection. Compared with histogram method, the algorithm using partitioning technology, combined with the relationship between spatial and color information. Experimental results show that the proposed method has stronger anti-interference performance compared with existing algorithms.