Ground plane segmentation for mobile robot visual navigation
- 13 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1513-1518
- https://doi.org/10.1109/iros.2001.977194
Abstract
We describe a method of mobile robot monocular vi- sual navigation, which uses multiple visual cues to de- tect and segment the ground plane in the robot's eld of view. Corner points are tracked through an image sequence and grouped into coplanar regions using a method which we call an H-based tracker. The H-based tracker employs planar homographys and is initialised by 5-point planar projective invariants. This allows us to detect ground plane patches and the colour within such patches is subsequently modelled. These patches are grown by colour classication to give a ground plane segmentation, which is then used as an input to a new variant of the articial potential eld algorithm.Keywords
This publication has 8 references indexed in Scilit:
- Real-time obstacle avoidance using central flow divergence, and peripheral flowIEEE Transactions on Robotics and Automation, 1998
- Quantitative planar region detectionInternational Journal of Computer Vision, 1996
- Divergent stereo in autonomous navigation: From bees to robotsInternational Journal of Computer Vision, 1995
- MOTION AND STRUCTURE FROM MOTION IN A PIECEWISE PLANAR ENVIRONMENTInternational Journal of Pattern Recognition and Artificial Intelligence, 1988
- A Combined Corner and Edge DetectorPublished by British Machine Vision Association and Society for Pattern Recognition ,1988
- The reconstruction of a plane surface from two perspective projectionsProceedings of the Royal Society of London. B. Biological Sciences, 1986
- Estimating three-dimensional motion parameters of a rigid planar patchIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981
- Random sample consensusCommunications of the ACM, 1981