Title :
A global 3D map-building approach using stereo vision
Author :
Saez, Juan Manuel ; Escolano, F.
Author_Institution :
Dept. de Ciencia de la Comput. e Inteligencia Artificial, Alicante Univ., Spain
fDate :
April 26 2004-May 1 2004
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 :
entropy; mobile robots; motion estimation; robot vision; stereo image processing; 3D map building method; action estimation algorithm; ego motion algorithm; energy minimization; entropy-based regularization; incremental matches filtering process; indoor mapping experiments; plane-parallel environments; quasirandom updating algorithm; robot; stereo camera; stereo vision; Cameras; Filtering algorithms; Iterative closest point algorithm; Matched filters; Minimization methods; Robot vision systems; Stereo vision; Terrain mapping; Three-dimensional displays;
Conference_Titel :
Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 IEEE International Conference on
Conference_Location :
New Orleans, LA, USA
Print_ISBN :
0-7803-8232-3
DOI :
10.1109/ROBOT.2004.1307987