首页    期刊浏览 2024年12月06日 星期五
登录注册

文章基本信息

  • 标题:Object Motion Detection Using Background Matching Framework
  • 本地全文:下载
  • 作者:M.A. Vinoth Kumar ; Dr. A. Kumaravel
  • 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
  • 关键词:Object motion detection; Cauchy Distribution; MTD; MSDE; Optical Flow.
国家哲学社会科学文献中心版权所有