DocumentCode :
2362707
Title :
A multi-camera 6-DOF pose tracker
Author :
Tariq, Sarah ; Dellaert, Frank
Author_Institution :
Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
fYear :
2004
fDate :
2-5 Nov. 2004
Firstpage :
296
Lastpage :
297
Abstract :
Most of the work in head-pose tracking has concentrated on single-camera systems with a relatively small field of view which have limited accuracy because features are only observed in a single viewing direction. We present a multicamera pose tracker that handles an arbitrary configuration of cameras rigidly fixed to the observer´s head. By using multiple cameras, we increase the robustness and accuracy by which a 6-DOF pose is tracked. However, in a multicamera rig setting, earlier methods for determining the unknown pose from three world-to-camera correspondences are no longer applicable. We present a RANSAC (M. Fischler and R. Bolles, 1981) based method that handles multicamera rigs by using a fast nonlinear minimization step in each RANSAC round.
Keywords :
cameras; computer vision; minimisation; motion estimation; tracking; RANSAC; fast nonlinear minimization; head-pose tracking; multicamera 6-DOF pose tracker; multicamera rigs; world-to-camera correspondences; Algorithms; Calibration; Cameras; Educational institutions; Equations; Gaussian noise; Machinery; Minimization methods; Noise measurement; Robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Mixed and Augmented Reality, 2004. ISMAR 2004. Third IEEE and ACM International Symposium on
Print_ISBN :
0-7695-2191-6
Type :
conf
DOI :
10.1109/ISMAR.2004.6
Filename :
1383084
Link To Document :
بازگشت