Panoramic representation for route recognition by a mobile robot
International Journal of Computer Vision - Special issue on machine vision research at Osaka University
Automatic Mountain Detection and Pose Estimation for Teleoperation of Lunar Rovers
Proceedings of the 5th International Symposium on Experimental Robotics V
Panoramic mosaics by manifold projection
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Position Estimation from Outdoor Visual Landmarks for Teleoperation of Lunar Rovers
WACV '96 Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV '96)
Mosaic based representations of video sequences and their applications
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
ELVIS: Eigenvectors for Land Vehicle Image System
IROS '95 Proceedings of the International Conference on Intelligent Robots and Systems-Volume 1 - Volume 1
Universal Mosaicing Using Pipe Projection
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Real-Time Omnidirectional Image Sensors
International Journal of Computer Vision - Special Issue on Omni-Directional Research in Japan
Robust Appearance Based Visual Route Following for Navigation in Large-scale Outdoor Environments
International Journal of Robotics Research
Hi-index | 0.00 |
This paper proposes a method for making a map of largescale environment based upon route scenes, assuming that thetopological relation of routes at intersections is known. A panoramicrepresentation is used for describing route scenes, and the number ofroutes connecting at an intersection is assumed to be known. The ideais to decompose a 2D graph into a number of closed loops. Bydetecting the closed loops and storing the relation among them, wecan describe the 2D map based upon route scenes. A robot can obtain aclosed loop by taking the same turn (leftmost for example) at everyintersection when it moves along routes. According to theinformation on routes at intersections, the robot can select unmovedroutes for finding new closed loops. By fusing new closed loops withfound ones, the robot can, further, build the map of environments.The effectiveness of our method are shown by experiment in areal-world environment.