DocumentCode :
495939
Title :
An efficient algorithm for extrinsic calibration between a 3D laser range finder and a stereo camera for surveillance
Author :
Aliakbarpour, H. ; Núñez, P. ; Prado, J. ; Khoshhal, K. ; Dias, J.
Author_Institution :
Dept. Electr. & Comput. Eng., Univ. of Coimbra, Coimbra, Portugal
fYear :
2009
fDate :
22-26 June 2009
Firstpage :
1
Lastpage :
6
Abstract :
The combined use of 3D laser range finders (LRF) and cameras is increasingly common in the navigation application for autonomous mobile robots. The integration of laser range information and images requires the estimation of the Euclidean 3-dimensional transformation between the coordinate systems of the LRF and the cameras. This paper describes a new and efficient method to perform the extrinsic calibration between a 3D LRF and a stereo camera with the aid of inertial data. The main novelty of the proposed approach compared to other state of the art calibration procedures is the use of an inertial measurement unit (IMU), which decreases the number of points needed to a robust calibration. Furthermore, a freely moving bright spot is the only calibration object. A set of virtual 3D points is made by waving the bright spot through the working volume in three different planes. Its projections onto the images are found with sub-pixel precision and verified by a robust RANSAC analysis. These same points are extracted according to the laser scan data and are corresponded to the virtual 3D points in the stereo pair. Experimental results presented in this paper demonstrate the accuracy of our approach. Furthermore, the applicability of the proposed technique is high, only requiring of an inertial sensor coupled to the sensor platform. This approach has been also extended for a camera network.
Keywords :
laser ranging; mobile robots; path planning; random processes; robot vision; stereo image processing; surveillance; 3D laser range finder; Euclidean 3D transformation; RANSAC analysis; autonomous mobile robot; extrinsic calibration; inertial measurement unit; random sample consensus; stereo camera; virtual 3D point; Calibration; Cameras; Data mining; Image analysis; Measurement units; Mobile robots; Navigation; Robot vision systems; Robustness; Surveillance;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advanced Robotics, 2009. ICAR 2009. International Conference on
Conference_Location :
Munich
Print_ISBN :
978-1-4244-4855-5
Electronic_ISBN :
978-3-8396-0035-1
Type :
conf
Filename :
5174703
Link To Document :
بازگشت