Share Email Print
cover

Proceedings Paper

Single image depth edges classification using a red, green, and blue light
Author(s): Matthias Voigt; Felix Ospald; Visvanathan Ramesh
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

Common image edge detectors identify a mixture of image discontinuities caused by a local change of illumination, texture or geometry. This document describes a method to separate depth-edges as a special instance of geometry edges from all other edges in a single image, without a complicated sensor. A single color camera and a red, green and blue light is used for scene illumination. Color shadows produced by the active illumination provide discriminative features to detect depth-edges. Experimental results are used to demonstrate the discriminative power of the proposed method and the performance of the depth-edge detection has been studied analytically for different illumination conditions.

Paper Details

Date Published: 10 October 2007
PDF: 10 pages
Proc. SPIE 6762, Two- and Three-Dimensional Methods for Inspection and Metrology V, 676205 (10 October 2007); doi: 10.1117/12.735745
Show Author Affiliations
Matthias Voigt, Siemens Corporate Research (United States)
Felix Ospald, Siemens Corporate Research (United States)
Visvanathan Ramesh, Siemens Corporate Research (United States)


Published in SPIE Proceedings Vol. 6762:
Two- and Three-Dimensional Methods for Inspection and Metrology V
Peisen S. Huang, Editor(s)

© SPIE. Terms of Use
Back to Top