TY - GEN
T1 - Gaussian mixture background model with shadow information
AU - Wang, Jung Ming
AU - Chen, Sei Wang
AU - Fuh, Chiou Shann
PY - 2011
Y1 - 2011
N2 - In this paper, we integrate shadow information into the background model of a scene in an attempt to detect both shadows and foreground objects at a time. Since shadows accompanying foreground objects are viewed as parts of the foreground objects, shadows will be extracted as well during foreground object detection. Shadows can distort object shapes and may connect multiple objects into one object. On the other hand, shadows tell the directions of light sources. In other words, shadows can be advantageous as well as disadvantageous. To begin, we use an adaptive Gaussian mixture model to describe the background of a scene. Based on this preliminary background model, we extract foreground objects and their accompanying shadows. Shadows are next separated from foreground objects through a series of intensity and color analyses. The characteristics of shadows are finally determined with the principal component analysis method and are embedded as an additional Gaussian in the background model. Experimental results demonstrated the feasibility of the proposed background model.
AB - In this paper, we integrate shadow information into the background model of a scene in an attempt to detect both shadows and foreground objects at a time. Since shadows accompanying foreground objects are viewed as parts of the foreground objects, shadows will be extracted as well during foreground object detection. Shadows can distort object shapes and may connect multiple objects into one object. On the other hand, shadows tell the directions of light sources. In other words, shadows can be advantageous as well as disadvantageous. To begin, we use an adaptive Gaussian mixture model to describe the background of a scene. Based on this preliminary background model, we extract foreground objects and their accompanying shadows. Shadows are next separated from foreground objects through a series of intensity and color analyses. The characteristics of shadows are finally determined with the principal component analysis method and are embedded as an additional Gaussian in the background model. Experimental results demonstrated the feasibility of the proposed background model.
KW - Adaptive Gaussian mixture model
KW - Dynamic scene
KW - Foreground detection
KW - Shadow detection
UR - http://www.scopus.com/inward/record.url?scp=84864994636&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864994636&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84864994636
SN - 9789728939489
T3 - Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011
SP - 217
EP - 222
BT - Proc. of the IADIS Int. Conf, Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011
T2 - IADIS International Conference Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conference on Computer Science and Information Systems 2011, MCCSIS 2011
Y2 - 24 July 2011 through 26 July 2011
ER -