Estimating location of land cover patch in super-resolution mapping by hopfield neural network

Siti Khadijah Mohd Zaki, Anuar Mikdad Muad

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Super-resolution mapping (SRM) aims to locate subpixel class fractions geographically in the area represented by a mixed pixel. The accuracy of small sub-pixel class patches are represented by the popular SRM method is explored. It is shown that the accuracy of predicted patch location from the Hopfield Neural of SRM is a function of patch size. Specifically, the accuracy with which patch location is predicted varies inversely with patch size, with very small patches subject to large mis-location errors. A means to reduce the magnitude of mis-location error through the use of multiple sub-pixel shifted imagery is illustrated and the implications to popular site-specific accuracy assessment discussed. The use of multiple subpixel shifted images was able to reduce the error in patch location by more than half for very small patches and represents a simple but effective enhancement to SRM applications.

Original languageEnglish
Title of host publicationISCAIE 2015 - 2015 IEEE Symposium on Computer Applications and Industrial Electronics
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages42-47
Number of pages6
ISBN (Print)9781479989690
DOIs
Publication statusPublished - 13 Oct 2015
EventIEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2015 - Langkawi, Malaysia
Duration: 12 Apr 201514 Apr 2015

Other

OtherIEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2015
CountryMalaysia
CityLangkawi
Period12/4/1514/4/15

Fingerprint

Hopfield neural networks
Pixels

Keywords

  • mixed pixel
  • multiple sub-pixel shifted
  • remote sensing

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Zaki, S. K. M., & Muad, A. M. (2015). Estimating location of land cover patch in super-resolution mapping by hopfield neural network. In ISCAIE 2015 - 2015 IEEE Symposium on Computer Applications and Industrial Electronics (pp. 42-47). [7298325] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAIE.2015.7298325

Estimating location of land cover patch in super-resolution mapping by hopfield neural network. / Zaki, Siti Khadijah Mohd; Muad, Anuar Mikdad.

ISCAIE 2015 - 2015 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2015. p. 42-47 7298325.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zaki, SKM & Muad, AM 2015, Estimating location of land cover patch in super-resolution mapping by hopfield neural network. in ISCAIE 2015 - 2015 IEEE Symposium on Computer Applications and Industrial Electronics., 7298325, Institute of Electrical and Electronics Engineers Inc., pp. 42-47, IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2015, Langkawi, Malaysia, 12/4/15. https://doi.org/10.1109/ISCAIE.2015.7298325
Zaki SKM, Muad AM. Estimating location of land cover patch in super-resolution mapping by hopfield neural network. In ISCAIE 2015 - 2015 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc. 2015. p. 42-47. 7298325 https://doi.org/10.1109/ISCAIE.2015.7298325
Zaki, Siti Khadijah Mohd ; Muad, Anuar Mikdad. / Estimating location of land cover patch in super-resolution mapping by hopfield neural network. ISCAIE 2015 - 2015 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 42-47
@inproceedings{ad1a18815efc4a07b2f296b5d7eec3b4,
title = "Estimating location of land cover patch in super-resolution mapping by hopfield neural network",
abstract = "Super-resolution mapping (SRM) aims to locate subpixel class fractions geographically in the area represented by a mixed pixel. The accuracy of small sub-pixel class patches are represented by the popular SRM method is explored. It is shown that the accuracy of predicted patch location from the Hopfield Neural of SRM is a function of patch size. Specifically, the accuracy with which patch location is predicted varies inversely with patch size, with very small patches subject to large mis-location errors. A means to reduce the magnitude of mis-location error through the use of multiple sub-pixel shifted imagery is illustrated and the implications to popular site-specific accuracy assessment discussed. The use of multiple subpixel shifted images was able to reduce the error in patch location by more than half for very small patches and represents a simple but effective enhancement to SRM applications.",
keywords = "mixed pixel, multiple sub-pixel shifted, remote sensing",
author = "Zaki, {Siti Khadijah Mohd} and Muad, {Anuar Mikdad}",
year = "2015",
month = "10",
day = "13",
doi = "10.1109/ISCAIE.2015.7298325",
language = "English",
isbn = "9781479989690",
pages = "42--47",
booktitle = "ISCAIE 2015 - 2015 IEEE Symposium on Computer Applications and Industrial Electronics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Estimating location of land cover patch in super-resolution mapping by hopfield neural network

AU - Zaki, Siti Khadijah Mohd

AU - Muad, Anuar Mikdad

PY - 2015/10/13

Y1 - 2015/10/13

N2 - Super-resolution mapping (SRM) aims to locate subpixel class fractions geographically in the area represented by a mixed pixel. The accuracy of small sub-pixel class patches are represented by the popular SRM method is explored. It is shown that the accuracy of predicted patch location from the Hopfield Neural of SRM is a function of patch size. Specifically, the accuracy with which patch location is predicted varies inversely with patch size, with very small patches subject to large mis-location errors. A means to reduce the magnitude of mis-location error through the use of multiple sub-pixel shifted imagery is illustrated and the implications to popular site-specific accuracy assessment discussed. The use of multiple subpixel shifted images was able to reduce the error in patch location by more than half for very small patches and represents a simple but effective enhancement to SRM applications.

AB - Super-resolution mapping (SRM) aims to locate subpixel class fractions geographically in the area represented by a mixed pixel. The accuracy of small sub-pixel class patches are represented by the popular SRM method is explored. It is shown that the accuracy of predicted patch location from the Hopfield Neural of SRM is a function of patch size. Specifically, the accuracy with which patch location is predicted varies inversely with patch size, with very small patches subject to large mis-location errors. A means to reduce the magnitude of mis-location error through the use of multiple sub-pixel shifted imagery is illustrated and the implications to popular site-specific accuracy assessment discussed. The use of multiple subpixel shifted images was able to reduce the error in patch location by more than half for very small patches and represents a simple but effective enhancement to SRM applications.

KW - mixed pixel

KW - multiple sub-pixel shifted

KW - remote sensing

UR - http://www.scopus.com/inward/record.url?scp=84959057369&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959057369&partnerID=8YFLogxK

U2 - 10.1109/ISCAIE.2015.7298325

DO - 10.1109/ISCAIE.2015.7298325

M3 - Conference contribution

AN - SCOPUS:84959057369

SN - 9781479989690

SP - 42

EP - 47

BT - ISCAIE 2015 - 2015 IEEE Symposium on Computer Applications and Industrial Electronics

PB - Institute of Electrical and Electronics Engineers Inc.

ER -