A Markov Chain Model for Semantic Indexing of Sport Program Sequences

In this paper, we propose a semantic indexing algorithm based on the controlled Markov chain modeling framework. Controlled Markov chain models are used to describe the temporal evolution of low-level visual descriptors extracted from the MPEG compressed bit-stream. To reduce the number of false detections given by the proposed video-processing algorithm, we have considered also the audio signal. In particular we have evaluated the "loudeness" associated to each video segments identified by the analysis carried out on the video signal. The intensity of the "loudness" has then been used to order the selected video segments. In this way, the segments associated to interesting events appear in the very first positions of the ordered list, and the number of false detections can be greatly reduced. The proposed algorithm has been conceived for soccer game video sequences, and the simulation results have shown the effectiveness of the proposed algorithm.