Improved codebook model based on spatio-temporal context

Author

Gan Huang ; Jiangqin Gui ; Weiyi He ; Guodong Wei ; Zihan Cong ; Dexiang Zhong ; Jianwei Zhang

Author_Institution

Sch. of Comput. Sci. & Eng., South China Univ. of Technol., Guangzhou, China

Volume

1

fYear

2014

fDate

13-16 July 2014

Firstpage

253

Lastpage

256

Abstract

Spatio-temporal context refers to the information of each pixel´s historical status and its adjacent pixels. The proposed algorithm applies the spatio-temporal context to the detection of foregrounds. It is based on the codebook model. For each pixel, a weight value is calculated according to the spatio-temporal context of this pixel to influence the detecting conditions. The algorithm can make the detecting results more accurate, especially in the interference regions such as the waving trees and the sudden illumination.

Keywords

image coding; object detection; adjacent pixels; foreground detection; illumination; improved codebook model; interference regions; object detection; pixel historical status; spatio-temporal context; waving trees; weight value; Abstracts; Context; Context modeling; Educational institutions; Gallium nitride; Real-time systems; Shape; Background subtraction; Codebook model; Object detection; Spatio-temporal context;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics (ICMLC), 2014 International Conference on

Conference_Location

Lanzhou

ISSN

2160-133X

Print_ISBN

978-1-4799-4216-9

Type

conf

DOI

10.1109/ICMLC.2014.7009125

Filename

7009125