DocumentCode :
3014064
Title :
Feature detection and matching in images with radial distortion
Author :
Lourenço, Miguel ; Barreto, João P. ; Malti, Abed
Author_Institution :
Inst. of Syst. & Robot., Univ. of Coimbra, Coimbra, Portugal
fYear :
2010
fDate :
3-7 May 2010
Firstpage :
1028
Lastpage :
1034
Abstract :
Image keypoints are broadly used in robotics for different purposes, ranging from recognition to 3D reconstruction, passing by SLAM and visual servoing. Robust keypoint matching across different views is problematic because of the relative motion between camera and scene that causes significant changes in feature appearance. The problem can be partially overcome by using state-of-the-art methods for keypoint detection and matching, that are resilient to common affine transformations such as changes in scale and rotation. Unfortunately, these approaches are not invariant to the radial distortion present in images acquired by cameras with wide field-of-view. This article proposes modifications to the Scale Invariant Feature Transform (SIFT), that improve the repeatability of detection and effectiveness of matching in the presence of distortion, while preserving the characteristics of invariance to scale and rotation. These modifications require an approximate modeling of the image distortion, and consist in using adaptative gaussian filtering for detection and implicit gradient correction for description. Extensive experiments, with both synthetic and real images, show that our method outperforms explicit distortion correction using image rectification.
Keywords :
feature extraction; filtering theory; image matching; image recognition; image reconstruction; robot vision; transforms; visual servoing; 3D image reconstruction; adaptative Gaussian filtering; affine transformations; camera; explicit distortion correction; feature detection; image distortion; image keypoint matching; image rectification; implicit gradient correction; radial distortion; scale invariant feature transform; visual servoing; Cameras; Computer vision; Filtering; Image recognition; Image reconstruction; Layout; Robot vision systems; Robustness; Simultaneous localization and mapping; Visual servoing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation (ICRA), 2010 IEEE International Conference on
Conference_Location :
Anchorage, AK
ISSN :
1050-4729
Print_ISBN :
978-1-4244-5038-1
Electronic_ISBN :
1050-4729
Type :
conf
DOI :
10.1109/ROBOT.2010.5509282
Filename :
5509282
Link To Document :
بازگشت