Robust edge extraction for SwissRanger SR-3000 range images

Author

Ye, Cang ; Hegde, Guruprasad M.

Author_Institution

Dept. of Appl. Sci., Univ. of Arkansas at Little Rock, Little Rock, AR, USA

fYear

2009

fDate

12-17 May 2009

Firstpage

2437

Lastpage

2442

Abstract

This paper presents a new method for extracting object edges from range images obtained by a 3D range imaging sensor the SwissRanger SR-3000. In range image preprocessing stage, the method enhances object edges by using surface normal information; and it employs the Hough Transform to detect straight line features in the Normal-Enhanced Range Image (NERI). Due to the noise in the sensor´s range data, a NERI contains corrupted object surfaces that may result in unwanted edges and greatly encumber the extraction of linear features. To alleviate this problem, a Singular Value Decomposition (SVD) filter is developed to smooth object surfaces. The efficacy of the edge extraction method is validated by experiments in various environments.

Keywords

Hough transforms; edge detection; feature extraction; filtering theory; image enhancement; image sensors; object detection; singular value decomposition; Hough transform; SwissRanger SR-3000 range image preprocessing; image enhancement; normal-enhanced range image; robust object edge extraction; singular value decomposition filter; straight line feature detection; Computer vision; Data mining; Feature extraction; Filters; Image edge detection; Image sensors; Object detection; Robustness; Sensor phenomena and characterization; Singular value decomposition;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 2009. ICRA '09. IEEE International Conference on

Conference_Location

Kobe

ISSN

1050-4729

Print_ISBN

978-1-4244-2788-8

Electronic_ISBN

1050-4729

Type

conf

DOI

10.1109/ROBOT.2009.5152559

Filename

5152559