Registration of visible and infrared images

Kristin Dana; P. Anandan

doi:10.1117/12.161433

Registration of visible and infrared images

Kristin Dana, P. Anandan

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

10 Scopus citations

Abstract

This paper presents an approach for registering images obtained from sensors tuned to significantly different regions of the electromagnetic spectrum. Standard correlation techniques for registration are not appropriate because of the inherent differences between the images. We present an approach which uses surface boundaries (obtained at multiple scales via an edge extraction process) to determine the affine transformation required to bring the images into registration. The affine parameters for registration are found by a hierarchical estimation process. A least squares gradient based technique is used to directly estimate the affine parameters from the blurred edges. Results of applying the algorithm to real image data are included.

Original language	English (US)
Pages (from-to)	2-13
Number of pages	12
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1957
DOIs	https://doi.org/10.1117/12.161433
State	Published - Oct 20 1993
Externally published	Yes
Event	Architecture, Hardware, and Forward-Looking Infrared Issues in Automatic Target Recognition 1993 - Orlando, United States Duration: Apr 11 1993 → Apr 16 1993

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.161433

Cite this

@article{6d9c899324934d8880804da720064352,

title = "Registration of visible and infrared images",

abstract = "This paper presents an approach for registering images obtained from sensors tuned to significantly different regions of the electromagnetic spectrum. Standard correlation techniques for registration are not appropriate because of the inherent differences between the images. We present an approach which uses surface boundaries (obtained at multiple scales via an edge extraction process) to determine the affine transformation required to bring the images into registration. The affine parameters for registration are found by a hierarchical estimation process. A least squares gradient based technique is used to directly estimate the affine parameters from the blurred edges. Results of applying the algorithm to real image data are included.",

author = "Kristin Dana and P. Anandan",

note = "Publisher Copyright: {\textcopyright} 1993 SPIE. All rights reserved.; Architecture, Hardware, and Forward-Looking Infrared Issues in Automatic Target Recognition 1993 ; Conference date: 11-04-1993 Through 16-04-1993",

year = "1993",

month = oct,

day = "20",

doi = "10.1117/12.161433",

language = "English (US)",

volume = "1957",

pages = "2--13",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Registration of visible and infrared images

AU - Dana, Kristin

AU - Anandan, P.

PY - 1993/10/20

Y1 - 1993/10/20

N2 - This paper presents an approach for registering images obtained from sensors tuned to significantly different regions of the electromagnetic spectrum. Standard correlation techniques for registration are not appropriate because of the inherent differences between the images. We present an approach which uses surface boundaries (obtained at multiple scales via an edge extraction process) to determine the affine transformation required to bring the images into registration. The affine parameters for registration are found by a hierarchical estimation process. A least squares gradient based technique is used to directly estimate the affine parameters from the blurred edges. Results of applying the algorithm to real image data are included.

AB - This paper presents an approach for registering images obtained from sensors tuned to significantly different regions of the electromagnetic spectrum. Standard correlation techniques for registration are not appropriate because of the inherent differences between the images. We present an approach which uses surface boundaries (obtained at multiple scales via an edge extraction process) to determine the affine transformation required to bring the images into registration. The affine parameters for registration are found by a hierarchical estimation process. A least squares gradient based technique is used to directly estimate the affine parameters from the blurred edges. Results of applying the algorithm to real image data are included.

UR - http://www.scopus.com/inward/record.url?scp=85038084668&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038084668&partnerID=8YFLogxK

U2 - 10.1117/12.161433

DO - 10.1117/12.161433

M3 - Conference article

AN - SCOPUS:85038084668

SN - 0277-786X

VL - 1957

SP - 2

EP - 13

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Architecture, Hardware, and Forward-Looking Infrared Issues in Automatic Target Recognition 1993

Y2 - 11 April 1993 through 16 April 1993

ER -

Registration of visible and infrared images

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this