Presentation

Discover background subtraction and BMC

You can use BMC to know how to use background subtraction thanks to OpenCV. This tutorial will help you to discover background subtraction, thanks to some videos available in BMC. To get more algorithms, we also recommend you to use the BGSLibrary, offering a lot of advanced background subtraction techniques. 

How to cite BMC?

You enjoyed using BMC 2012 benchmark? Please follow these two rules to cite our workshop

Antoine Vacavant, Thierry Chateau, Alexis Wilhelm and Laurent Lequièvre. A Benchmark Dataset for Foreground/Background Extraction. In ACCV 2012, Workshop: Background Models Challenge. Springer LNCS 7728, 291-300, November 2012, Daejeon, Korea.

Description

Background Models Challenge (BMC) is a competition for the comparison of background subtraction algorithms. The main topics of our workshop are

  • detection of moving objects, motion
    estimation ;

  • background / foreground modeling ;

  • signal, image processing ;

  • image segmentation ;

  • intelligent video-surveillance.

Many real-time vision-based applications devoted to video surveillance search for distinguishing moving objects from an image sequence given by a static camera. This background/foreground segmentation stage could be addressed by simple approaches, e.g. by computing the difference between two successive frames, or by building a time-averaged background image. However, such simple algorithms are very limited in outdoor environment for instance (because of global variation of luminance, shadows of objects, etc.).

Since this is an important step in video analysis, many background subtraction algorithms have been proposed since 90’s to tackle these problems. Although the evaluation of BSA is an important issue, relevant papers that handle with both benchmarks and annotated dataset are limited. Moreover, many authors that propose a novel approach use classic techniques as a gold-standards, but rarely compare their method with recent related work. BMC is thus an opportunity for researchers at both universities and companies to evaluate the quality of their work.