Foreground segmentation using adaptive mixture models in color and depth

Segmentation of novel or dynamic objects in a scene, often referred to as “background subtraction” or foreground segmentation”, is a critical early in step in most computer vision applications in domains such as surveillance and human-computer interaction. All previously described, real-time methods fail to handle properly one or more common phenomena, such as global illumination changes, shadows, inter-reflections, similarity of foreground color to background and non-static backgrounds (e.g. active video displays or trees waving in the wind). The advent of hardware and software for real-time computation of depth imagery makes better approaches possible. We propose a method for modeling the background that uses per-pixel, time-adaptive, Gaussian mixtures in the combined input space of depth and luminance-invariant color. This combination in itself is novel, but we further improve it by introducing the ideas of (1) modulating the background model learning rate based on scene activity, and (2) making color-based segmentation criteria dependent on depth observations. Our experiments show that the method possesses much greater robustness to problematic phenomena than the prior state-of-the-art, without sacrificing real-time performance, making it well-suited for a wide range of practical applications in video event detection and recognition