This paper introduces ViBe (Visual Background Extractor), a universal background subtraction algorithm designed to detect and segment moving objects in video sequences. ViBe incorporates several innovative mechanisms, such as storing a set of past values at the same or nearby pixel locations and comparing them to the current pixel value to determine if it belongs to the background. Unlike traditional methods that replace oldest values first, ViBe randomly selects values from the background model for substitution. When a pixel is identified as part of the background, its value is propagated to neighboring pixels. The method is detailed in full, including pseudo-code and parameter values, and is compared to other background subtraction techniques. ViBe outperforms state-of-the-art methods in terms of computation speed and detection rate. A simplified version of the algorithm, requiring only one comparison and one byte of memory per pixel, is also analyzed and shown to perform better than mainstream techniques. The implementation of ViBe is available at http://www.motiondetection.org.This paper introduces ViBe (Visual Background Extractor), a universal background subtraction algorithm designed to detect and segment moving objects in video sequences. ViBe incorporates several innovative mechanisms, such as storing a set of past values at the same or nearby pixel locations and comparing them to the current pixel value to determine if it belongs to the background. Unlike traditional methods that replace oldest values first, ViBe randomly selects values from the background model for substitution. When a pixel is identified as part of the background, its value is propagated to neighboring pixels. The method is detailed in full, including pseudo-code and parameter values, and is compared to other background subtraction techniques. ViBe outperforms state-of-the-art methods in terms of computation speed and detection rate. A simplified version of the algorithm, requiring only one comparison and one byte of memory per pixel, is also analyzed and shown to perform better than mainstream techniques. The implementation of ViBe is available at http://www.motiondetection.org.