English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Computer vision applications based on videos often require the detection ofmoving objects in their first step. Background subtraction is then applied inorder to separate the background and the foreground. In literature, backgroundsubtraction is surely among the most investigated field in computer visionproviding a big amount of publications. Most of them concern the application ofmathematical and machine learning models to be more robust to the challengesmet in videos. However, the ultimate goal is that the background subtractionmethods developed in research could be employed in real applications liketraffic surveillance. But looking at the literature, we can remark that thereis often a gap between the current methods used in real applications and thecurrent methods in fundamental research. In addition, the videos evaluated inlarge-scale datasets are not exhaustive in the way that they only covered apart of the complete spectrum of the challenges met in real applications. Inthis context, we attempt to provide the most exhaustive survey as possible onreal applications that used background subtraction in order to identify thereal challenges met in practice, the current used background models and toprovide future directions. Thus, challenges are investigated in terms ofcamera, foreground objects and environments. In addition, we identify thebackground models that are effectively used in these applications in order tofind potential usable recent background models in terms of robustness, time andmemory requirements.

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