Determining three‐dimensional structure from image sequences given by horizontal and vertical moving camera

Publisher Website
Google Scholar
Abstract
Stereovision is the simplest method for acquiring three‐dimensional information. A problem then is that sometimes it is difficult to establish a correspondence between the left and right images in such cases as: (1) multiple correspondence; (2) occlusion; (3) positional reversals; and (4) horizontal edge. This paper proposes a method to determine the three‐dimensional structure of the scene from the sequences of images obtained by moving camera. First, a two‐dimensional image is constructed from the sequence of images in which the apparent locus of motion is represented as a segment. The corresponding problem here is simplified as the detection of segments on the synthetic image. By examining the relations among the detected segments, the occlusions can be detected, and the correspondence can be established where positional reversals occur. By moving the camera not only in one direction, but also in orthogonal directions, the unique correspondence can be established, independently of the direction of the edge. An input system was constructed which can accept a large number of stereo image sequences with a high speed, and a complex three‐dimensional structure of the scene was actually restored.

This publication has 5 references indexed in Scilit: