Comparative analysis of Background Subtraction techniques and applications

Background Subtraction is a preliminary technique used for video surveillance, moving object detection, human machine interaction, gait recognition, multimedia applications etc. A range of algorithms have been introduced over the years and tested over different databases with ground truth. The goal of this study is to provide a comparative analysis of available background subtraction algorithms classified as basic, statistical, machine learning, and others techniques. The methods are compared based on their advantages, disadvantages and performance against the challenges like shadow detection, camera jitter and dynamic background. This paper presents a framework (techniques, dataset, application) for researchers in identifying the unfertile areas of background subtraction analysis.