Indian Journal of Science and Technology
Year: 2015, Volume: 8, Issue: Supplementary 10, Pages: 1-6
Pavel V. Skribtsov* , Sergey O. Surikov and Michael A. Yakovlev
PAWLIN Technologies Ltd, Dubna, Russian Federation; [email protected]
New simple and fast method for robust background image estimation from video stream is offered. The method is based on Markov Random Field, Belief Propagation and DBSCAN algorithms. The usage of cyclic graph MRF model of nonoverlapping image patches with narrow set of background hypotheses generated by DBSCAN algorithm provides faster convergence of Belief Propagation with accuracy comparable to the state-of-art methods.
Keywords: Background Estimation, Belief Propagation, DBSCAN, Markov Random Field
Subscribe now for latest articles and news.