Depth estimation from disparity of stereo images

S. Mitra, S. L. Lim, D. J. Lee, B. S. Nutter

Research output: Contribution to journalConference articlepeer-review

Abstract

The extraction of depth information from stereo image disparities, using a 2-D power cepstrum technique as well as the usual correlation technique, is presented. The edges of the input stereo images were enhanced by a Laplacian of Gaussian (LoG) operator modified for fast implementation. The depth of an object surface is calculated from a simple nonconvergent triangulation technique. The methodology presented in this paper allows a fast yet accurate implementation of computational stereo vision in a machine vision system. The basic concepts of the present paper have been further extended and a motion stereo model has been developed for reconstruction of three-dimensional (3-D) geometry of natural objects using time-sequenced images with capabilities of yielding dense depth maps.

Original languageEnglish
Pages (from-to)216-226
Number of pages11
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume1349
StatePublished - 1990
EventApplications of Digital Image Processing XIII - San Diego, CA, USA
Duration: Jul 10 1990Jul 13 1990

Fingerprint Dive into the research topics of 'Depth estimation from disparity of stereo images'. Together they form a unique fingerprint.

Cite this