Performance analysis of moving object detection using BGS techniques in visual surveillance

Abstract

Over the last decennium, the object detection is the pivotal step in any machine vision and image processing application. It is the initial step applied to extract most informative pixel from the video stream. Many algorithms are available in literature for extraction of visual information or foreground object from video sequence. This paper also provides a detailed overview of both conventional and traditional approaches used for detection of object. This paper explores various related methods, major challenges, applications, resources such as datasets, web-sources, etc. This paper presents a detailed overview of a moving object detection using background subtraction techniques in the video surveillance system that provide safety in cities, towns or home when video sequence is captured using IP cameras. The experimental work of this paper is performed over change detection, I2R, and wallflower datasets. The experimental work also depicts a comparative analysis of some of the peer methods. This work demonstrates several performance metrics to check robustness of the compared state-of-the-art methods.