DocumentCode :
3524560
Title :
On the importance of modeling camera calibration uncertainty in visual SLAM
Author :
Ozog, Paul ; Eustice, Ryan M.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Univ. of Michigan, Ann Arbor, MI, USA
fYear :
2013
fDate :
6-10 May 2013
Firstpage :
3777
Lastpage :
3784
Abstract :
This paper reports on methods for incorporating camera calibration uncertainty into a two-view sparse bundle adjustment (SBA) framework. The co-registration of two images is useful in mobile robotics for determining motion over time. These camera measurements can constrain a robot´s relative poses so that the trajectory and map can be estimated in a technique known as simultaneous localization and mapping (SLAM). Here, we comment on the importance of propagating uncertainty in both feature extraction and camera calibration in visual pose-graph SLAM. We derive an improved pose covariance estimate that leverages the Unscented Transform, and compare its performance to previous methods in both simulated and experimental trials. The two experiments reported here involve data from a camera mounted on a KUKA robotic arm (where a precise ground-truth trajectory is available) and a Hovering Autonomous Underwater Vehicle (HAUV) for large-scale autonomous ship hull inspection.
Keywords :
SLAM (robots); calibration; cameras; feature extraction; image registration; mobile robots; pose estimation; robot vision; HAUV; KUKA robotic arm; SBA framework; camera calibration uncertainty modelling; camera measurements; feature extraction; hovering autonomous underwater vehicle; image co-registration; large-scale autonomous ship hull inspection; mobile robotics; pose covariance estimation; robot relative pose; simultaneous localization and mapping; two-view sparse bundle adjustment framework; unscented transform; visual pose-graph SLAM; Calibration; Cameras; Robot vision systems; Simultaneous localization and mapping; Uncertainty; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation (ICRA), 2013 IEEE International Conference on
Conference_Location :
Karlsruhe
ISSN :
1050-4729
Print_ISBN :
978-1-4673-5641-1
Type :
conf
DOI :
10.1109/ICRA.2013.6631108
Filename :
6631108
Link To Document :
بازگشت