TY - GEN
T1 - Spatially adaptive illumination modeling for background subtraction
AU - Paruchuri, Jithendra K.
AU - Sathiyamoorthy, Edwin P.
AU - Cheung, Sen Ching S.
AU - Chen, Chung Hao
PY - 2011
Y1 - 2011
N2 - Background subtraction is important for many vision applications. Existing techniques can adapt to gradual changes in illumination but fail to cope with sudden changes often seen in indoor environment. In this paper, we propose a novel background subtraction technique that models the change of illumination as a regression function of spatial image coordinates. Such spatial dependency is significant when light sources are close to or within the scene. The regression function is learned from highly probable background regions and applied to the rest of the background models to compensate for the illumination change. While a single regression function is adequate for a smooth Lambertian surface, multiple regression functions are needed to handle depth discontinuities, shadows, and non-Lambertian surfaces. The change of illumination is first segmented and different regression functions are applied to different segments. Experimental results comparing our techniques with other schemes show better foreground segmentation during illumination change.
AB - Background subtraction is important for many vision applications. Existing techniques can adapt to gradual changes in illumination but fail to cope with sudden changes often seen in indoor environment. In this paper, we propose a novel background subtraction technique that models the change of illumination as a regression function of spatial image coordinates. Such spatial dependency is significant when light sources are close to or within the scene. The regression function is learned from highly probable background regions and applied to the rest of the background models to compensate for the illumination change. While a single regression function is adequate for a smooth Lambertian surface, multiple regression functions are needed to handle depth discontinuities, shadows, and non-Lambertian surfaces. The change of illumination is first segmented and different regression functions are applied to different segments. Experimental results comparing our techniques with other schemes show better foreground segmentation during illumination change.
UR - http://www.scopus.com/inward/record.url?scp=84863075979&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84863075979&partnerID=8YFLogxK
U2 - 10.1109/ICCVW.2011.6130460
DO - 10.1109/ICCVW.2011.6130460
M3 - Conference contribution
AN - SCOPUS:84863075979
SN - 9781467300629
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 1745
EP - 1752
BT - 2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011
T2 - 2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011
Y2 - 6 November 2011 through 13 November 2011
ER -