Automated multisensor polyhedral model acquisition

Conference item

We describe a method for automatically generating accurate piecewise planar models of indoor scenes using a combination of a 2D laser scanner and a camera on a mobile platform. The method exploits the complementarity of the sensors. Mapping techniques applied to 2D laser scans simultaneously compute a map and the location of the sensor in the unknown environment. This provides an initial estimate for the vision algorithms by compensating for rotation, foreshortening and scale change between images. The vision algorithms are then able to compute a very accurate registration (via a plane to plane homography) which is used to segment the model into planar facets, and to improve the estimate of the model and sensor position. Results are demonstrated on a man made scene using a 2D laser scanner and a calibrated camera mounted on a trolley.

Authors: Ortin, D; Montiel, JMM; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Host title: 2003 IEEE International Conference on Robotics and Automation
• Pages: 1007-1012
• Publication date: 2003-11-10
• Event title: IEEE International Conference on Robotics and Automation (ICRA 2003)
• Event location: Taipei, Taiwan
• Event start date: 2003-05-12
• Event end date: 2003-05-17
• DOI: 10.1109/robot.2003.1241724
• ISSN: 1050-4729
• ISBN: 0780377362
• Language: English
• Keywords: robustness; simultaneous localization and mapping; robot vision systems; layout; sonar detection; laser modes; computer vision; robot sensing systems; image reconstruction; cameras