ViBe is a universal background subtraction algorithm that efficiently detects moving objects in video sequences. The algorithm stores a set of past pixel values for each pixel and compares them to the current pixel value to determine if it belongs to the background. It adaptively updates the background model by randomly replacing values, which differs from traditional methods that prioritize replacing the oldest values first. When a pixel is identified as background, its value is propagated to neighboring pixels, enhancing spatial consistency. The algorithm is compared with other background subtraction techniques, showing superior performance in terms of computation speed and detection rate. A simplified version of ViBe requires only one comparison and one byte of memory per pixel, outperforming mainstream techniques even in its minimal form. The algorithm is implemented at http://www.motiondetection.org. Background subtraction involves distinguishing moving objects (foreground) from static or slowly moving parts of a scene (background). Traditional methods often struggle with dynamic backgrounds, varying lighting, and complex scenes. ViBe addresses these challenges by using a conservative update policy, ensuring that foreground values are never included in the background model. It also incorporates a memoryless update policy, allowing samples to decay exponentially in relevance over time, and spatial consistency through background sample propagation. ViBe's effectiveness is demonstrated through experimental results, where it outperforms other algorithms in terms of accuracy and efficiency. The algorithm is parameter-free in terms of video frame rate or color space, making it adaptable to various scenarios. It is suitable for embedded systems due to its low computational requirements and efficient memory usage. The algorithm's unique properties, such as the memoryless update policy and spatial consistency, enable it to handle dynamic backgrounds and structural changes effectively.ViBe is a universal background subtraction algorithm that efficiently detects moving objects in video sequences. The algorithm stores a set of past pixel values for each pixel and compares them to the current pixel value to determine if it belongs to the background. It adaptively updates the background model by randomly replacing values, which differs from traditional methods that prioritize replacing the oldest values first. When a pixel is identified as background, its value is propagated to neighboring pixels, enhancing spatial consistency. The algorithm is compared with other background subtraction techniques, showing superior performance in terms of computation speed and detection rate. A simplified version of ViBe requires only one comparison and one byte of memory per pixel, outperforming mainstream techniques even in its minimal form. The algorithm is implemented at http://www.motiondetection.org. Background subtraction involves distinguishing moving objects (foreground) from static or slowly moving parts of a scene (background). Traditional methods often struggle with dynamic backgrounds, varying lighting, and complex scenes. ViBe addresses these challenges by using a conservative update policy, ensuring that foreground values are never included in the background model. It also incorporates a memoryless update policy, allowing samples to decay exponentially in relevance over time, and spatial consistency through background sample propagation. ViBe's effectiveness is demonstrated through experimental results, where it outperforms other algorithms in terms of accuracy and efficiency. The algorithm is parameter-free in terms of video frame rate or color space, making it adaptable to various scenarios. It is suitable for embedded systems due to its low computational requirements and efficient memory usage. The algorithm's unique properties, such as the memoryless update policy and spatial consistency, enable it to handle dynamic backgrounds and structural changes effectively.