Efficient planar features matching for robot localization using GPU
Authors:
- 1 June 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21607508,p. 16-23
Abstract
Matching image features between an image and a map of landmarks is usually a time consuming process in mobile robot localization or Simultaneous Localisation And Mapping algorithms. The main problem is being able to match features in spite of viewpoint changes. Methods based on interest point descriptors such as SIFT have been implemented on GPUs to reach real time performance. In this paper, we present another way to match features with the use of a local 3D model of the features and a motion model of the robot. This matching algorithm dedicated to robot localization would be much too slow if executed on a CPU. Thanks to a GPU implementation, we show that it is possible to achieve real-time performance while offering more robustness than descriptor based methods.Keywords
This publication has 8 references indexed in Scilit:
- Efficient keypoint matching for robot vision using GPUs2009
- Matching Planar Features for Robot LocalizationLecture Notes in Computer Science, 2009
- Using planar facets for stereovision SLAM2008
- Fast scale invariant feature detection and matching on programmable graphics hardware2008
- Locally Planar Patch Features for Real-Time Structure from Motion2004
- Object recognition from local scale-invariant features1999
- A Fully Projective Formulation to Improve the Accuracy of Lowe's Pose-Estimation AlgorithmComputer Vision and Image Understanding, 1998
- A Combined Corner and Edge Detector1988