ViBe - a powerful technique for background detection and subtraction in video sequences

Executive summary


ViBe is a powerful pixel-based technique that detects the background in video sequences. Many experiments have shown that it performs better than the state-of-the-art techniques known in the scientific literature. In addition the computational load is lower than simple background techniques implemented in commercial products. ViBe is the perfect solution for both software and hardware implementations.

Code and program for Windows and Linux (details this page for how to use them)

Due to copyright and patent infringments, we have been forced to change our distribution policy; we apologize for this.
The following programs are accessible to academic researchers only (follow the links, and ask for the permission to download the programs. Please provide some evidence that you are a researcher in an academic institution; requests from gmail, yahoo, hotmail, 163, etc, e-mail accounts will be refused).

What about the processing speed?

To give an idea on how fast ViBe runs, we have tested ViBe on a cubieboard platform [1G ARM cortex-A8 processor, NEON, VFPv3, 256KB L2 cache], with the Ubuntu/linaro OS. The framerate is 23 fps for a VGA size (640x480) monochrome uncompressed data stream.

Licensing opportunities

ViBe is protected by several patents (patent track: WO2009007198 / Publication date: 2009-01-15; Priority number(s): EP20070112011 20070708) / Europe (granted): EP2015252 / US (granted): US 8009918 B2 (pdf) / Japan (granted): JP 2011 4699564 B2
The University of Liege holds all intellectual rights on the technology and the innovations have been validated during the patent track.
For licensing the technology, please contact Mr. Van der Elstraeten [University of Liege] or [].

Major advantages:




For any question, please contact Prof. Van Droogenbroeck .
See also the site of the Interface, in charge of the partnerships between companies and the University of Liege.

ViBe inside a digital camera

Illustrations for a static camera

View from the roof of a house

Illustrations for a moving camera

Global and local motions are estimated via optical flow on a pre-defined grid of pixels [preliminary work].

Camera in motion

ULg      Institut Montefiore