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
User
Information