Video Segmentation Using Hidden Markov Model with Multimodal Features

In this paper, a video segmentation algorithm based on Hidden Markov Model classifier with multimodal feature is proposed. By using Hidden Markov Model classifier with both audio and visual features, erroneous shot boundary detection and over-segmentation were avoided compared with conventional algorithms. The experimental results show that the propose method is effective in shot detection.

• Type: Conference
• Year: 2004
• Where: CIVR
• Authors: Tae Meon Bae, Sung Ho Jin, Yong Man Ro
• Keywords: CIVR 2004, Hidden Markov Model, Image Analysis, Markov Model Classifier, Shot Boundary Detection