Title :
Stereo Motion from Feature Matching and Tracking
Author :
Gilbert, Sébastien ; Laganière, Robert ; Roth, Gerhard
Author_Institution :
Sch. of Inf. Technol. & Eng., Ottawa Univ., Ont.
Abstract :
This paper presents a 3D pose estimation and reconstruction system based on a calibrated stereoscopic vision setup. The proposed approach consists in robustly tracking the movements of the cameras with respect to a rigid scene along a sequence. In addition, a novel correction scheme is proposed, that compensates for the accumulated error in the computed positions, exploiting the detection of loops in the movement. Experiments are presented to assess the accuracy of the resulting 3D measurements
Keywords :
computer vision; feature extraction; image reconstruction; motion estimation; stereo image processing; tracking; 3D pose estimation; calibrated stereoscopic vision setup; correction scheme; feature matching; feature tracking; reconstruction system; stereo motion; Calibration; Cameras; Error correction; Image reconstruction; Information technology; Layout; Position measurement; Robot vision systems; Robustness; Tracking; 3D reconstruction; Computer vision; camera calibration; non-contact measurement; position measurement; stereoscopic vision;
Conference_Titel :
Instrumentation and Measurement Technology Conference, 2005. IMTC 2005. Proceedings of the IEEE
Conference_Location :
Ottawa, Ont.
Print_ISBN :
0-7803-8879-8
DOI :
10.1109/IMTC.2005.1604346