Object Motion Detection in Video Frames Using Background Frame Matching

In this project we present detection the motion in video frames using background frame Matching. These document video surveillance systems have become widely available to ensure safety and security in both the public and private sectors due to incidents of terrorist activity and other social problems. This paper proposes a novel motion detection method with a background model module and an object mask generation module with moving camera. We propose a selfadaptive background matching method to select the background pixel at each frame with regard to background model generation. The quality of the proposed method is analyzed. The experimental results show that our proposed method has high accuracy and performance compared to previous methods using static camera. Keywords— Object motion detection, Cauchy Distribution, MTD, MSDE, Optical Flow.