We propose a new method for combining two overlapping maps made by the stereo vision technique utilizing view field information. Degree of matching is evaluated for every matching candidate, where object point pairs and solitary points in the overlapping view fields contribute positive and negative values, respectively. The threshold value used in judging pair is determined by considering the error magnitude, which depends on the distance from the view point. Various kinds of calculation are compared in terms of the freedom of threshold, which is defined as the ratio of the maximum and minimum threshold values, and with which the correct overlap is derived.>

We propose a new approach for mcasuring 30 positions of target objects using stereo vision system. In stereo vision metrology for natural scenes , automatic recognition of targets and detcrminination of corresponding points arc strongly desired , which technique as of today is so poor that these processes are relied on human asislance. Automatic recognition and stereo correspondensc of telephone poles in a pair of natural scenes is realized by using an algorithm considering specifications of the targets, such as diameter, height, installation condition, through four steps, that is, [ I] Search region resDiction, [ O] Recognition, [U] Correspondence and [IV] Examination.

A simple and useful calibration method for a TV camera with a high-distortion lens is presented. The parameters to be calibrated are effective focal length, one-pixel width on an image plane, image distortion center, and distortion coefficient. A simple-pattern calibration chart composed of parallel straight lines is introduced as a reference for calibration. An ordinary 2D model fitting is decomposed into two 1D model fittings on the column and row of a frame buffer across the image distortion center by ingeniously utilizing the point symmetry characteristic of image distortion. Some parameters with a calibration chart are eliminated by setting up a calibration chart precisely and by utilizing negligibly low distortion near the image distortion center. Thus, the number of unknown parameters to be calibrated is drastically decreased, enabling simple and useful calibration. The effectiveness of the proposed calibration method is confirmed by experimentation.>