Improved Camshift Tracking Algorithm Based on Silhouette Moving Detection

Author

Zou, Tengyue ; Tang, Xiaoqi ; Song, Bao

Author_Institution

Sch. of Mech. Sci., Huazhong Univ. of Sci. & Tech., Wuhan, China

fYear

2011

fDate

4-6 Nov. 2011

Firstpage

11

Lastpage

15

Abstract

Camshift is an efficient object tracking algorithm using color probability distribution. But it´s easy to be interfered by the similar color objects in the background. So we bring in the motion characteristics extracted by the motion template method, and then make an improved Camshift algorithm. Experiments show that the improved algorithm has more robustness in dealing with color interference and sudden illumination variation.

Keywords

feature extraction; image colour analysis; image denoising; motion estimation; object tracking; statistical distributions; Camshift tracking algorithm; Silhouette moving detection; color object interference; color probability distribution; motion characteristics extraction; motion template method; object tracking algorithm; sudden illumination variation; Color; Image color analysis; Lighting; Probability distribution; Robustness; Target tracking; Camshift; Motion template; Silhouette; Tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Information Networking and Security (MINES), 2011 Third International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4577-1795-6

Type

conf

DOI

10.1109/MINES.2011.16

Filename

6103711