多数カメラからの入力画像とCAD図形情報を組合せた認識手法に関する研究

概要

論文の詳細を見る
In this paper, we propose a recognition method comparing characteristics of three dimensional CAD information with those of input images of several cameras. Several cameras are installed upper and lateral side of a recognition area to estimate three dimensional coordinates of vertexes which compose an object. Three vertexes of the object are determined in the input images taken by those cameras. Straight lines which go through the above mentioned vertexes are estimated, and three dimensional coordinates of vertexes (intersections) are calculated from those straight lines. Finally, the kind and direction of the object are determined by comparing the distance among vertexes and the normal vector of a plane made by three vertexes with those in DXF file of three-dimensional CAD figures.
1999-06-25