12 March 1988 A Computational Model For Sensing Depth From A Single 2-D Image
Author Affiliations +
Proceedings Volume 0850, Optics, Illumination, and Image Sensing for Machine Vision II; (1988) https://doi.org/10.1117/12.942869
Event: Advances in Intelligent Robotics Systems, 1987, Cambridge, CA, United States
Abstract
It is generally a difficult task to obtain a complete geometrical model of a scene given a limited number of storage spaces, or to construct a 3-D scene geometry from one or more 2-D images. In this paper we focus on extracting information about a 3-D scene geometry given a 2-D image. The degree of blurriness (or sharpness) gives rise to computation of depth of an object. A method of shape from sharpness, based on this concept, is introduced. Given a point source image, its distance from a lens is obtained. This can be applied to an arbitrary scene consisting of superposition of many point sources.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
M. R. Sayeh, M. R. Sayeh, M. Daneshdoost, M. Daneshdoost, F. Pourboghrat, F. Pourboghrat, } "A Computational Model For Sensing Depth From A Single 2-D Image", Proc. SPIE 0850, Optics, Illumination, and Image Sensing for Machine Vision II, (12 March 1988); doi: 10.1117/12.942869; https://doi.org/10.1117/12.942869
PROCEEDINGS
4 PAGES


SHARE
Back to Top