Kazuhiko Saka

TL;DR: In this article, a system for recognizing a three-dimensional object includes a plurality of image pickup apparatus, e.g., TV cameras, by which images of the object are picked up from at least three directions.

TL;DR: In this paper, the position and orientation of a geometric figure are detected by sequentially producing the coordinates with respect to an orthogonal coordinate system of pixels which make up an image of the geometric figure.

TL;DR: A pattern outline tracking system as discussed by the authors provides the functions that include scanning an object to be recognized and providing a series of analog video signals, comparing a video signal level with the specific, variable threshold level, providing a binary signal consisting of a sequence of serial bits, holding the binary signal bits as the input image pattern in an image memory, deriving partial patterns sequentially from the serial binary signals bits, matching the partial patterns against the corresponding reference patterns containing the previously defined starting points to be tracked.

TL;DR: In this paper, the three coordinate data of a feature point from two corresponding object images by respective both-eye stereoscopic systems A 12, A 23, A 13 as the three-dimensional coordinates of the same object point and the truth/falsehood of respective corresponding object point images is judged by the geometric restriction condition of respective coordinate data r 12, r 23, r 13.

TL;DR: In this paper, the 3D coordinates of a point P are obtained in the form of an intersecting point among straight lines FAPA, FBPB and FCPC, where the feature points PA-PC are opposite to each other as images at the point P.