A Comparative Approach of Human Motion Detection Methods in video Surveillance Application –A Review

Abstract

Identifying the moving objects from a video sequence is the fundamental and critical task in robotics, surveillance and many computer vision applications. According to the result of moving object detection research on video sequences, this work gives a review on existing methods and proposes a comparative analysis using statistical methods and self organizing method to detect moving object . We are using Background Subtraction and Self Organizing Background Subtraction (SOBS) algorithm for moving object detection. In Background Subtraction establishing a reliable background updating model based on statistical and use a dynamic optimization threshold method to obtain a more complete moving object. While in SOBS approach to moving object detection based on neural background model automatically generated by a self organizing approach. The proposed method runs quickly, accurately and fits for the real-time detection

Keywords: Background subtraction; background model; moving object detection, Self organizing, visual surveillance