Review and Classification of Trending Background Subtraction-Based Object Detection Techniques

Object detection in the surveillance video is in favor of both researchers and industries due to its wide benefits and broad usage in numerous applications. Human activity monitoring and controlling the flow of people in airports are among critical applications that need rigid control and surveillance. This paper presents state-of-the-art algorithms of background subtraction-based object detection techniques. The techniques are W4 Method, Mixture of Gaussian, Three Frame Differencing, Differencing and Summing Technique, KDE, CodeBook, Fuzzy Logic Based, SACON, BNN, SOBS, Vibe, RaBS and PBAS. This work makes a vital contribution to the existing field of study. It differs from other similar recently published works by providing the following: (1) categorization/classifications of the methods namely recursive/parametric approaches and non-recursive/non-parametric approaches (2) stating most of the prominent methods used in this field in a hierarchical way (3) explaining pros and cons of each methods and their performance (4) presenting the gaps exist at the end of each method that can open the understanding and doors to new researches and/or improvements.