Models for automatic classi cation of video

In this paper, we explore a technique for automatic classiication of video sequences, (such as a TV broadcast, movies). This technique analyses the incoming video sequences and classiies them into categories. It can be viewed as an on-line parser for video signals. We present two techniques for automatic classiication. In the rst technique, the incoming video sequence is analyzed to extract the motion information. This information is optimally projected onto a single dimension. This projection information is then used to train Hidden Markov Models (HMMs) that eeciently and accurately classify the incoming video sequence. Preliminary results with 50 diierent test sequences (25 Sports and 25 News sequences) indicate a classiication accuracy of 90% by the HMM models. In the second technique, 24 full length motion picture trailers are classiied using HMMs. This classiication is compared with the internet movie database and we nd that they correlate well. Only two out of 24 trailers were classiied incorrectly.