#100: Event detection and semantic identification using Bayesian belief networks

M. H. Kolekar, K. Palaniappan, S. Sengupta, and G. Seetharaman

IEEE Int. Conf. Computer Vision Workshops, pgs. 554--561, 2009

fmv, motion, features, fusion, visual events, data mining, cbir

PlainText, Bibtex, PDF, URL, DOI, Google Scholar


A probabilistic Bayesian belief network (BBN) based framework is proposed for semantic analysis and summa- rization of video using event detection. Our approach is customized for soccer but can be applied to other types of sports video sequences. We extract excitement clips from soccer sports video sequences that are comprised of mul- tiple subclips corresponding to the events such as replay, field-view, goalkeeper, player, referee, spectator, players’ gathering. The events are detected and classified using a hierarchical classification scheme. The BBN based on observed events is used to assign semantic concept-labels, such as goals, saves, and card to each excitement clip. The collection of labeled excitement clips provide a video sum- mary for highlight browsing, video skimming, indexing and retrieval. The proposed scheme offers a general approach to automatic tagging large scale multimedia content with rich semantics. Our tests using soccer video shows that the pro- posed semantic identification framework is more efficient.