STEREO MATCHING USING A NEURAL NETWORK.

Y. T. Zhou; R. Chellappa

STEREO MATCHING USING A NEURAL NETWORK.

Research output: Contribution to journal › Conference article › peer-review

Abstract

A polynomial is fitted to find a smooth continuous intensity function in a window and the first-order intensity derivatives are estimated. A neural network is then used to implement the matching procedure under the epipolar, photometric and smoothness constraints, using the estimated first-order derivatives. Owing to the dense intensity derivatives a dense array of disparities is generated with only a few iterations. The method does not require surface interpolation. Computer simulations to demonstrate the efficacy of the method are presented.

Original language	English (US)
Pages (from-to)	940-943
Number of pages	4
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
State	Published - 1988
Externally published	Yes

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Cite this

@article{647250a3b839419e9cf4a50692f77c4d,

title = "STEREO MATCHING USING A NEURAL NETWORK.",

abstract = "A polynomial is fitted to find a smooth continuous intensity function in a window and the first-order intensity derivatives are estimated. A neural network is then used to implement the matching procedure under the epipolar, photometric and smoothness constraints, using the estimated first-order derivatives. Owing to the dense intensity derivatives a dense array of disparities is generated with only a few iterations. The method does not require surface interpolation. Computer simulations to demonstrate the efficacy of the method are presented.",

author = "Zhou, {Y. T.} and R. Chellappa",

year = "1988",

language = "English (US)",

pages = "940--943",

journal = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

issn = "0736-7791",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - STEREO MATCHING USING A NEURAL NETWORK.

AU - Zhou, Y. T.

AU - Chellappa, R.

PY - 1988

Y1 - 1988

N2 - A polynomial is fitted to find a smooth continuous intensity function in a window and the first-order intensity derivatives are estimated. A neural network is then used to implement the matching procedure under the epipolar, photometric and smoothness constraints, using the estimated first-order derivatives. Owing to the dense intensity derivatives a dense array of disparities is generated with only a few iterations. The method does not require surface interpolation. Computer simulations to demonstrate the efficacy of the method are presented.

AB - A polynomial is fitted to find a smooth continuous intensity function in a window and the first-order intensity derivatives are estimated. A neural network is then used to implement the matching procedure under the epipolar, photometric and smoothness constraints, using the estimated first-order derivatives. Owing to the dense intensity derivatives a dense array of disparities is generated with only a few iterations. The method does not require surface interpolation. Computer simulations to demonstrate the efficacy of the method are presented.

UR - http://www.scopus.com/inward/record.url?scp=0023672105&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023672105&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0023672105

SN - 0736-7791

SP - 940

EP - 943

JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -

STEREO MATCHING USING A NEURAL NETWORK.

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this