Title :
Monocular-vision based SLAM using Line Segments
Author :
Lemaire, Thomas ; Lacroix, Simon
Author_Institution :
LAAS-CNRS, Toulouse
Abstract :
This paper presents a method to incorporate 3D line segments in vision based SLAM. A landmark initialization method that relies on the Plucker coordinates to represent a 3D line is introduced: a Gaussian sum approximates the feature initial state and is updated as new observations are gathered by the camera. Once initialized, the landmarks state is estimated along an EKF-based SLAM approach: constraints associated with the Plucker representation are considered during the update step of the Kalman filter. The whole SLAM algorithm is validated in simulation runs and results obtained with real data are presented.
Keywords :
Gaussian processes; Kalman filters; SLAM (robots); edge detection; feature extraction; image representation; robot vision; 3D line segments; Gaussian sum; Plucker coordinates; Plucker representation; SLAM; camera; extended Kalman filter; feature initial state approximation; landmark initialization; landmarks state estimation; monocular vision; Cameras; Delay estimation; Image segmentation; Robot kinematics; Robot sensing systems; Robot vision systems; Robotics and automation; Sampling methods; Simultaneous localization and mapping; State estimation;
Conference_Titel :
Robotics and Automation, 2007 IEEE International Conference on
Conference_Location :
Roma
Print_ISBN :
1-4244-0601-3
Electronic_ISBN :
1050-4729
DOI :
10.1109/ROBOT.2007.363894