A global 3D map-building approach using stereo vision
Authors:
- 1 January 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10504729) , 1197-1202 Vol.2
Abstract
We present a stereo-based approach for building 3D maps. First, the best local alignment between successive point clouds is computed by a fast ego-motion/action-estimation algorithm which relies on an incremental matches filtering process followed by energy minimization. Then, a quasi-random updating algorithm, a kind of multi-view ICP, minimizes the global inconsistency of the map. Such an inconsistency is defined in terms of the sum of local inconsistencies and an additional entropy-based regularization term which is effective in plane-parallel environments. For the sake of efficiency, we assume a flat floor and a fixed stereo camera mounted on the robot. We have successfully tested the approach by performing several indoor mapping experiments.Keywords
This publication has 13 references indexed in Scilit:
- Learning compact 3D models of indoor and outdoor environments with a mobile robotRobotics and Autonomous Systems, 2003
- Real-time acquisition of compact volumetric 3D maps with mobile robots2003
- Vision-based mapping with backward correction2003
- Compact Mapping in Plane-Parallel Environments Using Stereo VisionLecture Notes in Computer Science, 2003
- Sensor based creation of indoor virtual environment models2002
- Vision-based mobile robot localization and mapping using scale-invariant features2002
- A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping2002
- Design, architecture and control of a mobile site-modeling robot2002
- Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual LandmarksThe International Journal of Robotics Research, 2002
- Using Real-Time Stereo Vision for Mobile Robot NavigationAutonomous Robots, 2000