期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：4
DOI：10.15680/ijircce.2015.0304246
出版社：S&S Publications
摘要：This document VIDEO surveillance systems have become widely available to ensure safety and securityin both the public and private sectors due to incidents of terrorist activity and other social problems. In the previoussystems motion is detected using static camera. This paper proposes a novel motion detection method with abackground model module and an object mask generation module with moving camera. The moving camera capturesmonocular video of a scene and identifies those moving objects which are characteristically human. This serves as botha proof-of concept and a verification of other existing algorithms for human motion detection. We propose a selfadaptivebackground matching method to select the background pixel at each frame with regard to background modelgeneration. Then the binary mask is generated using Cauchy distribution model. The quality of the proposed method isanalyzed. The experimental results show that our proposed method has high accuracy and performance compared toprevious methods using static camera
