Title :
A hybrid codebook background model for background subtraction
Author :
Sun, I-Ting ; Hsu, Shih-Chung ; Huang, Chung-Lin
Author_Institution :
Dept. of Electr. Eng., Nat. Tsing-Hua Univ., Hsinchu, Taiwan
Abstract :
Real-time segmentation of scene into foreground and background is an important issue for many applications. Different from previous codebook (CB) methods, this paper introduces a hybrid CB model by combining the mixture of Gaussian (MOG) method and the CB method. It can be used to solve the problems of moving background and shadow/highlight on the background and background. Our method avoids extracting false foreground pixels or missing real foreground pixels. The experimental results illustrate the advantages of our method over the other methods.
Keywords :
Gaussian processes; image segmentation; MOG method; background subtraction; hybrid CB model; hybrid codebook background model; mixture-of-Gaussian method; real-time segmentation; Brightness; Color; Lighting; Power harmonic filters; Shape; Training; Vectors; Background Subtraction; Codebook (CB) model; Mixture of Gaussian (MOG); Shadow removal;
Conference_Titel :
Signal Processing Systems (SiPS), 2011 IEEE Workshop on
Conference_Location :
Beirut
Print_ISBN :
978-1-4577-1920-2
DOI :
10.1109/SiPS.2011.6088956