Feature detection and matching in images with radial distortion
Authors:
- 1 May 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10504729,p. 1028-1034
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
This publication has 11 references indexed in Scilit:
- Optimal Large View Visual Servoing with Sets of SIFT FeaturesProceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (cat. No.01ch37164), 2007
- Scale-Invariant Features on the Sphere2007
- A Comparison of Affine Region DetectorsInternational Journal of Computer Vision, 2005
- A spherical eye from multiple cameras (makes better models of the world)2005
- Simultaneous linear estimation of multiple view geometry and lens distortion2005
- Geometric properties of central catadioptric line images and their application in calibrationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- What is the center of the image?2002
- Ego-motion and omnidirectional cameras2002
- Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual LandmarksThe International Journal of Robotics Research, 2002
- A Representation for Shape Based on Peaks and Ridges in the Difference of Low-Pass TransformIEEE Transactions on Pattern Analysis and Machine Intelligence, 1984