Improved parameters updating algorithm for the detection of moving objects

Abstract

The presence of dynamic scene is a challenging problem in video surveillance systems tasks. Mixture of Gaussian (MOG) is the most appropriate method to model dynamic background. However, local variations and the instant variations in the brightness decrease the performance of the later. We present in this paper a novel and efficient method that will significantly reduce MOG drawbacks by an improved parameters updating algorithm. Starting from a normalization step, we divide each extracted frame into several blocks. Then, we apply an improved updating algorithm for each block to control local variation. When a significant environment changes are detected in one or more blocs, the parameters of MOG assigned to these blocks are updated and the parameters of the rest remain the same. Experimental results demonstrate that the proposed approach is effective and efficient compared with state-ofthe- art background subtraction methods.