Share Email Print
cover

Proceedings Paper

Feature-based approach to reconstruction of 3D objects from digital images
Author(s): Yong Ru Huang; John Charles Trinder
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Three-dimensional object reconstruction is a basic problem in machine vision for object recognition and inspection. In this paper, we present an automatic procedure to construct 3-D objects by edge-based feature extraction. We intend to describe extracted objects in terms of simple geometry which corresponds to the description of the design model. In a method developed for edge detection with sub-pixel accuracy, the direction of the edge is attached to each edge point as a primitive for succeeding processes. The line segmentation method is applied to slip and merge edges into straight lines or regular curves in terms of the primitives. These lines can then be linked in terms of terminals by the constraints of distance and orientation to form surface patches. Using two or more CCD cameras, the 3-D surface of the object can be reconstructed by matching the same geometric properties in stereo images with the addition of the epipolar line technique.

Paper Details

Date Published: 17 August 1994
PDF: 8 pages
Proc. SPIE 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision, (17 August 1994); doi: 10.1117/12.182848
Show Author Affiliations
Yong Ru Huang, Univ. of New South Wales (Australia)
John Charles Trinder, Univ. of New South Wales (Australia)


Published in SPIE Proceedings Vol. 2357:
ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision
Heinrich Ebner; Christian Heipke; Konrad Eder, Editor(s)

© SPIE. Terms of Use
Back to Top