Comparative Analysis of Moving Object Detection Algorithms

Moving object detection plays a key role in surveillance systems, vehicle and robot guidance, regardless of it is a very troublesome task. Detecting as well as tracking objects in the video so as to distinguish motion features has been rising as a concerning research/study area in image processing/computer vision fields. One of the current demanding study area in computer/machine vision domain are humans and vehicles motion video surveillance system in a dynamic environment. It is considered as a big challenge for researchers to design a good detection technique which is computationally efficient and consuming less time. Moving object detection algorithms must be fast, reliable and vigorous to make video surveillance systems so as to avoid terrorism, crime and etc. This paper presents comparison of different detection schemes for segmenting/detecting moving objects from the background environment. The algorithms are adequate for adapting to dynamic scene condition, removing shadowing, and distinguishing/identifying removed objects both in complex indoor and outdoor. These algorithms are frame/temporal differencing (FD), simple adaptive background subtraction (BS), Mixture of Gaussian Model (MoG) and approximate median filter. These algorithms are appropriate for real time surveillance applications and each of them have their own advantages and drawbacks.