Stereo Error Detection, Correction, and Evaluation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robot Vision
A System to Navigate a Robot into a Ship Structure
ICVS '01 Proceedings of the Second International Workshop on Computer Vision Systems
A Four-step Camera Calibration Procedure with Implicit Image Correction
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Hi-index | 0.00 |
In any measuring system the categorization of the error generation factors leads to simplification of complex error problems and to higher suppression of the error. In this paper we categorize, quantify and analyze the errors that affect a binocular active vision head. Simulations have been made and experimental results on a high resolution pan-tilt-vergence mechanism are also proposed. As a conclusion it can be said that the system performs optimal when it is initialized so that the two cameras are perfectly aligned and perpendicular to the baseline. Small variations in the vergence angle or small horizontal deviations of the principal point alters the measurement dramatically. On the other hand, variations in pan and tilt and vertical deviations of the principal point, affect the measurement insignificantly.