Building a Robust Appearance Model for Object Tracking

Author

Yao, Zhijun ; Bin Feng ; Wang, Junwei ; Liu, Wenyu

Author_Institution

Dept. of Electron. & Inf. Eng., HuaZhong Univ. of Sci. & Technol., Wuhan, China

Volume

3

fYear

2009

fDate

7-8 Nov. 2009

Firstpage

471

Lastpage

475

Abstract

One of the challenges to creating robust trackers is the construction of robust appearance Model. This paper presents a robust appearance model for object tracking. The robust object distribution is acquired by comparing the two Gaussian Mixture Models of the object and background. The probability image generated by the robust object distribution is used for the CAMSHIFT tracking. Experiments on several video sequences show the effectiveness of the proposed method.

Keywords

Gaussian processes; computer vision; object detection; probability; tracking; CAMSHIFT tracking; Gaussian mixture models; object tracking; probability image; robust appearance model; robust object distribution; Application software; Artificial intelligence; Buildings; Computational intelligence; Computer vision; Feature extraction; Histograms; Noise robustness; Probability; Target tracking; CAMSHIFT; Computer Vision; Feature Extraction; Gaussian Mixture Model; Object Tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4244-3835-8

Electronic_ISBN

978-0-7695-3816-7

Type

conf

DOI

10.1109/AICI.2009.165

Filename

5376764