Weighted Samples Based Background Modeling for the Task of Motion Detection in Video Sequences

Abstract

In this paper,a non parametric method for background subtraction and moving object detection based on adaptive threshold using successive squared differences and including frame differencing process is proposed. the presented scheme focused on the case of adaptive threshold and dependent distance calculation using a weighted estimation procedure. In contrast with the existing update procedures (Firstin First-out, random pickup), We proposed an intuitive update policy to the background model based onassociated decreasing weights. The presented algorithm succeeds on extracting the moving foreground with efficiency and overpasses the problematic of ghost situations. The proposed framework provides robustness to noise. Experiments show competitive results compared to existing approaches and demonstrate the applicability of the proposed scheme in a variety of video surveillance scenarios.