An Evaluation of Background Subtraction for Object Detection Vis-a-Vis Mitigating Challenging Scenarios

Background subtraction is a popular technique for detecting objects moving across a fixed camera view. The performance of this paradigm is influenced by various challenges, such as object relocation, illumination change, cast shadows, waving background, camera shake, bootstrapping, camouflage, and so on. In this paper, we present a synopsis on the evolution of the background subtraction techniques over the last two decades. The different ways of mathematical modeling are taken into consideration to categorize the methods. We also evaluate the performance of some of the state-of-the-art techniques vis-a-vis the challenges associated. Eleven different algorithms of background subtraction have been simulated on thirty-four image sequences collected from five benchmark datasets. For each image sequence, seven performance metrics are evaluated and an exhaustive comparative analysis has been made to derive inferences. The potential findings in the result analysis are presented for future exploration.