A Novel Method of Suppressing Stochastic Errors in Circle Center Locating

Author

Li Qin ; Da Feipeng ; Zhang Hu

Author_Institution

Colledge of Autom.., Southeast Univ., Nanjing, China

fYear

2009

fDate

4-6 Nov. 2009

Firstpage

1

Lastpage

5

Abstract

The location of a circular target plays an important role in the computer vision. The two invariants in the perspective projection model of camera imaging process is analyzed and a five-point constraints and the optimization object function based on cross-ratio and the straightness of the fitting line is put forward, and then a method of suppressing stochastic errors in the location of circle centers with the help of hybrid particle swarm algorithm is established. The experiment shows that the method is effective to correct the circle centers´ stochastic error. This method could be applied to vision detection and camera calibration to get more accurate locating information of the feature points. Thus it has some theoretical meanings and practical values.

Keywords

cameras; computer vision; feature extraction; particle swarm optimisation; stochastic processes; camera calibration; camera imaging process; circle center location; computer vision detection; cross-ratio; feature point; fitting line straightness; hybrid particle swarm algorithm; optimization object function; perspective projection model; stochastic error suppression; Algorithm design and analysis; Calibration; Cameras; Computer errors; Computer vision; Constraint optimization; Error correction; Image analysis; Particle swarm optimization; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2009. CCPR 2009. Chinese Conference on

Conference_Location

Nanjing

Print_ISBN

978-1-4244-4199-0

Type

conf

DOI

10.1109/CCPR.2009.5344119

Filename

5344119