Title :
Foreground segmentation using adaptive mixture models in color and depth
Author :
Harville, Michael ; Gordon, Gaile ; Woodfill, John
Author_Institution :
Hewlett-Packard Co., Palo Alto, CA, USA
Abstract :
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
Keywords :
Gaussian processes; adaptive signal processing; computer vision; image colour analysis; image matching; image segmentation; video signal processing; active video displays; adaptive mixture models; background model learning rate; background subtraction; color imagery; color matching; color-based segmentation; computer vision applications; depth imagery; depth observations; dynamic objects; foreground color similarity; foreground segmentation; global illumination changes; human-computer interaction; inter-reflections; luminance-invariant color; nonstatic backgrounds; per-pixel Gaussian mixtures; real-time computation; real-time methods; scene activity; shadows; software; surveillance; time-adaptive Gaussian mixtures; video event detection; video event recognition; Displays; Event detection; Focusing; Hardware; Layout; Lighting; Milling machines; Reliability engineering; Robustness; Surveillance;
Conference_Titel :
Detection and Recognition of Events in Video, 2001. Proceedings. IEEE Workshop on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7695-1293-3
DOI :
10.1109/EVENT.2001.938860