A gradient algorithm for stereo matching without correspondence

J. Zhou; B. K. Ghosh

doi:10.1109/9.544006

A gradient algorithm for stereo matching without correspondence

J. Zhou, B. K. Ghosh

Mathematics and Statistics

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

In this paper we study the problem of feature point matching via a technique well known in geometry, leading to a new gradient algorithm in machine vision. The procedure does not require one to solve explicit correspondences between feature points but relies on a specific form of "spatial averaging." In this sense the estimation procedure is robust. In this paper we describe the algorithm and report simulation results.

Original language	English
Pages (from-to)	1671-1676
Number of pages	6
Journal	IEEE Transactions on Automatic Control
Volume	41
Issue number	11
DOIs	https://doi.org/10.1109/9.544006
State	Published - 1996

Access to Document

10.1109/9.544006

Cite this

@article{04b65e1b7b4a484d8dfac7d3de430b4b,

title = "A gradient algorithm for stereo matching without correspondence",

abstract = "In this paper we study the problem of feature point matching via a technique well known in geometry, leading to a new gradient algorithm in machine vision. The procedure does not require one to solve explicit correspondences between feature points but relies on a specific form of {"}spatial averaging.{"} In this sense the estimation procedure is robust. In this paper we describe the algorithm and report simulation results.",

author = "J. Zhou and Ghosh, {B. K.}",

year = "1996",

doi = "10.1109/9.544006",

language = "English",

volume = "41",

pages = "1671--1676",

journal = "IEEE Transactions on Automatic Control",

issn = "0018-9286",

number = "11",

}

TY - JOUR

T1 - A gradient algorithm for stereo matching without correspondence

AU - Zhou, J.

AU - Ghosh, B. K.

PY - 1996

Y1 - 1996

N2 - In this paper we study the problem of feature point matching via a technique well known in geometry, leading to a new gradient algorithm in machine vision. The procedure does not require one to solve explicit correspondences between feature points but relies on a specific form of "spatial averaging." In this sense the estimation procedure is robust. In this paper we describe the algorithm and report simulation results.

AB - In this paper we study the problem of feature point matching via a technique well known in geometry, leading to a new gradient algorithm in machine vision. The procedure does not require one to solve explicit correspondences between feature points but relies on a specific form of "spatial averaging." In this sense the estimation procedure is robust. In this paper we describe the algorithm and report simulation results.

UR - http://www.scopus.com/inward/record.url?scp=0030284687&partnerID=8YFLogxK

U2 - 10.1109/9.544006

DO - 10.1109/9.544006

M3 - Article

AN - SCOPUS:0030284687

VL - 41

SP - 1671

EP - 1676

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

SN - 0018-9286

IS - 11

ER -

A gradient algorithm for stereo matching without correspondence

Abstract

Access to Document

Other files and links

Fingerprint

Cite this