An improved ViBe background subtraction method based on region motion classification
Ying Chu, Jiong Chen, Xia Chen · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2013
Motion detection plays an important role in intelligent video surveillance. This paper introduces a particular background subtraction technique called ViBe. This technique updates the background model randomly and it has established model with fast, high precision and fast processing speed. ViBe algorithm provides the method of updated background model, but slowly eliminates ghost region. This paper presents an improved ViBe algorithm based on region motion classification. The algorithm considers the difference of the movement directions of feature points in foreground regions on adjacent frame, and defines a criterion function to evaluate the difference so that can quickly eliminate ghost regions. Experimental results show that the proposed algorithm quickly remove the ghost region and improve the detection accuracy.