Abstract | ||
---|---|---|
We introduce an approach for realtime segmenta- tion of a scene into foreground objects, background, and object shadows superimposed on the back- ground. To segment foreground objects, we use an adaptive thresholding method, which is able to deal with rapid changes of the overall brightness. The segmented image usually includes shadows cast by the objects onto the background. Our approach is able to robustly remove the shadow from the back- ground while preserving the silhouette of the fore- ground object. We discuss a similarity measure for comparing color pixels, which improves the qual- ity of shadow removal significantly. As the image segmentation is part of a real-time interaction envi- ronment, real-time processing is needed. Our im- plementation allows foreground segmentation and robust shadow removal with 15 Hz. |
Year | Venue | Keywords |
---|---|---|
2003 | VMV | real time,adaptive thresholding,real time processing,image segmentation |
Field | DocType | Citations |
Background subtraction,Similarity measure,Computer graphics (images),Silhouette,Computer science,Image segmentation,Artificial intelligence,Thresholding,Computer vision,Shadow,Pattern recognition,Segmentation,Pixel | Conference | 25 |
PageRank | References | Authors |
1.36 | 5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Grest | 1 | 129 | 10.65 |
Jan-Michael Frahm | 2 | 2847 | 141.20 |
Reinhard Koch | 3 | 2038 | 170.17 |