摘要：Based on rough sets (RS), a novel rapid shot boundary detection algorithm was proposed in discrete cosine transform (DCT) compressed domain. First, DCT coefficients and DC coefficients are extracted from video sequences, so an information system is constructed with DC coefficient. Second, information system is reduced by ruduction theory of RS, the representation of the video frame is obtained by reduced DC coefficients. Finally, by introducing subdividing theory of RS, the frames of video are segmented objectively. The experimental results show that the algorithm can achieve higher performance. Compared to conventional algorithm, the algorithm enjoys many advantages. Firstly, only a subset of frames needs to be considered during analysis, allowing the reduction of the computational complexity, so the algorithm can avoid the expensive computations in decompression processes. Secondly, the relativity of segmentation of video shot becomes more scientific than earlier methods. Its robustness and effectiveness are validated by experiments with various kinds of video sequences.
