A Proposed Background Modeling Algorithm for Moving Object Detection Using Statistical Measures

Abstract

Extracting moving object from video sequence is one of the most important steps
in the video-based analysis. Background subtraction is the most commonly used
moving object detection methods in video, in which the extracted object will be
feed to a higher-level process ( i.e. object localization, object tracking ).
The main requirement of background subtraction method is to construct a
stationary background model and then to compare every new coming frame with it
in order to detect the moving object.
Relied on the supposition that the background occurs with the higher appearance
frequency, a proposed background reconstruction algorithm has been presented
based on pixel intensity classification ( PIC ) approach. First, pixel intensity in a
predetermined time period has been classified according to a proposed clustering
method, second, pixels frequency of those clusters has been calculated, finally, the
center of the cluster with the higher pixel frequency has been chosen as the
background pixel intensity value.
The efficiency and effectiveness of the proposed algorithm has been confirmed
through comparing its results with those of the most common traditional methods,
besides , the results of the proposed algorithm in a number of testing environment
which are traffic monitoring and pedestrian surveillance shows that the proposed
algorithm can save space and economize computation time and give good accuracy.