Title :
Removing Shadows and Ghosts with an Improved Background Mixture Model
Author :
Zhu, Zhenli ; He, Yujing
Author_Institution :
Fire Dept. of Hebei Province, Shijiazhuang, China
Abstract :
We describe an improved background mixture model to detect motion and remove illumination changes, shadows and ghosts. The shadows and ghosts detection processing is fused with updating background subtraction model after the frame is transformed to Hue Saturation Value (HSV) color space from Red Green Blue (RGB) color space in order to reduce the effect of illumination changes, shadows and ghosts. Compared with the traditional background mixture model, the improved method can avoid the bad effect of shadows and ghosts, and it is highly computationally cost-effective.
Keywords :
image colour analysis; image recognition; motion estimation; video surveillance; HSV; RGB; background mixture model improvement; background subtraction model; ghosts detection processing; hue saturation value; illumination changes; red green blue color space; shadow detection processing; Automation; Decision support systems; Virtual reality;
Conference_Titel :
Intelligent Computation Technology and Automation (ICICTA), 2010 International Conference on
Conference_Location :
Changsha
Print_ISBN :
978-1-4244-7279-6
Electronic_ISBN :
978-1-4244-7280-2
DOI :
10.1109/ICICTA.2010.898
