Background Subtraction in Real Applications: Challenges, Current Models and Future Directions

TL;DR

This paper surveys the use of background subtraction in real-world computer vision applications, highlighting practical challenges, current models, and future research directions to bridge the gap between research and practice.

Contribution

It provides an exhaustive review of real application challenges, analyzes current background models used in practice, and suggests future directions for more robust solutions.

Findings

Identifies key challenges in real applications including camera, foreground, and environment issues.

Highlights the gap between research models and practical deployment.

Recommends potential background models suitable for real-world use.

Abstract

Computer vision applications based on videos often require the detection of moving objects in their first step. Background subtraction is then applied in order to separate the background and the foreground. In literature, background subtraction is surely among the most investigated field in computer vision providing a big amount of publications. Most of them concern the application of mathematical and machine learning models to be more robust to the challenges met in videos. However, the ultimate goal is that the background subtraction methods developed in research could be employed in real applications like traffic surveillance. But looking at the literature, we can remark that there is often a gap between the current methods used in real applications and the current methods in fundamental research. In addition, the videos evaluated in large-scale datasets are not exhaustive in the way that they only covered a part of the complete spectrum of the challenges met in real applications. In this context, we attempt to provide the most exhaustive survey as possible on real applications that used background subtraction in order to identify the real challenges met in practice, the current used background models and to provide future directions. Thus, challenges are investigated in terms of camera, foreground objects and environments. In addition, we identify the background models that are effectively used in these applications in order to find potential usable recent background models in terms of robustness, time and memory requirements.