Super-resolution analysis for accurate mapping of land cover and land cover pattern

Anuar Mikdad Muad, Giles M. Foody

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

3 Citations (Scopus)

Abstract

This paper presents a super-resolution mapping technique as a means to gain accurate information of land cover, and especially its spatial pattern, at a sub-pixel scale. This technique extends the application of an established Hopfield neural network of super-resolution mapping technique by providing its input with a fusion of a time series coarse spatial but fine temporal resolution images. To illustrate this technique, a series of daily MODIS 250m images was acquired and fused. Using a Landsat ETM+ 30m image as ground data, results demonstrated that a Hopfield network that uses time series information produces significantly more accurate representation of land cover mapping in terms of thematic accuracy and spatial pattern prediction than by using a single image into Hopfield network or into hard classification techniques.

Original languageEnglish
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
Pages502-505
Number of pages4
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010 - Honolulu, HI
Duration: 25 Jul 201030 Jul 2010

Other

Other2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010
CityHonolulu, HI
Period25/7/1030/7/10

Fingerprint

land cover
Time series
time series
Hopfield neural networks
image resolution
Image resolution
MODIS
Landsat
pixel
Fusion reactions
Pixels
prediction
analysis

Keywords

  • Fine temporal resolution
  • Hopfield neural network
  • Land cover spatial pattern
  • MODIS 250m
  • Super-resolution mapping

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)
  • Computer Science Applications

Cite this

Muad, A. M., & Foody, G. M. (2010). Super-resolution analysis for accurate mapping of land cover and land cover pattern. In International Geoscience and Remote Sensing Symposium (IGARSS) (pp. 502-505). [5649083] https://doi.org/10.1109/IGARSS.2010.5649083

Super-resolution analysis for accurate mapping of land cover and land cover pattern. / Muad, Anuar Mikdad; Foody, Giles M.

International Geoscience and Remote Sensing Symposium (IGARSS). 2010. p. 502-505 5649083.

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

Muad, AM & Foody, GM 2010, Super-resolution analysis for accurate mapping of land cover and land cover pattern. in International Geoscience and Remote Sensing Symposium (IGARSS)., 5649083, pp. 502-505, 2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010, Honolulu, HI, 25/7/10. https://doi.org/10.1109/IGARSS.2010.5649083
Muad AM, Foody GM. Super-resolution analysis for accurate mapping of land cover and land cover pattern. In International Geoscience and Remote Sensing Symposium (IGARSS). 2010. p. 502-505. 5649083 https://doi.org/10.1109/IGARSS.2010.5649083
Muad, Anuar Mikdad ; Foody, Giles M. / Super-resolution analysis for accurate mapping of land cover and land cover pattern. International Geoscience and Remote Sensing Symposium (IGARSS). 2010. pp. 502-505
@inproceedings{cbbd5667552b49489db6d82590cf5c17,
title = "Super-resolution analysis for accurate mapping of land cover and land cover pattern",
abstract = "This paper presents a super-resolution mapping technique as a means to gain accurate information of land cover, and especially its spatial pattern, at a sub-pixel scale. This technique extends the application of an established Hopfield neural network of super-resolution mapping technique by providing its input with a fusion of a time series coarse spatial but fine temporal resolution images. To illustrate this technique, a series of daily MODIS 250m images was acquired and fused. Using a Landsat ETM+ 30m image as ground data, results demonstrated that a Hopfield network that uses time series information produces significantly more accurate representation of land cover mapping in terms of thematic accuracy and spatial pattern prediction than by using a single image into Hopfield network or into hard classification techniques.",
keywords = "Fine temporal resolution, Hopfield neural network, Land cover spatial pattern, MODIS 250m, Super-resolution mapping",
author = "Muad, {Anuar Mikdad} and Foody, {Giles M.}",
year = "2010",
doi = "10.1109/IGARSS.2010.5649083",
language = "English",
isbn = "9781424495658",
pages = "502--505",
booktitle = "International Geoscience and Remote Sensing Symposium (IGARSS)",

}

TY - GEN

T1 - Super-resolution analysis for accurate mapping of land cover and land cover pattern

AU - Muad, Anuar Mikdad

AU - Foody, Giles M.

PY - 2010

Y1 - 2010

N2 - This paper presents a super-resolution mapping technique as a means to gain accurate information of land cover, and especially its spatial pattern, at a sub-pixel scale. This technique extends the application of an established Hopfield neural network of super-resolution mapping technique by providing its input with a fusion of a time series coarse spatial but fine temporal resolution images. To illustrate this technique, a series of daily MODIS 250m images was acquired and fused. Using a Landsat ETM+ 30m image as ground data, results demonstrated that a Hopfield network that uses time series information produces significantly more accurate representation of land cover mapping in terms of thematic accuracy and spatial pattern prediction than by using a single image into Hopfield network or into hard classification techniques.

AB - This paper presents a super-resolution mapping technique as a means to gain accurate information of land cover, and especially its spatial pattern, at a sub-pixel scale. This technique extends the application of an established Hopfield neural network of super-resolution mapping technique by providing its input with a fusion of a time series coarse spatial but fine temporal resolution images. To illustrate this technique, a series of daily MODIS 250m images was acquired and fused. Using a Landsat ETM+ 30m image as ground data, results demonstrated that a Hopfield network that uses time series information produces significantly more accurate representation of land cover mapping in terms of thematic accuracy and spatial pattern prediction than by using a single image into Hopfield network or into hard classification techniques.

KW - Fine temporal resolution

KW - Hopfield neural network

KW - Land cover spatial pattern

KW - MODIS 250m

KW - Super-resolution mapping

UR - http://www.scopus.com/inward/record.url?scp=78650856186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650856186&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2010.5649083

DO - 10.1109/IGARSS.2010.5649083

M3 - Conference contribution

AN - SCOPUS:78650856186

SN - 9781424495658

SN - 9781424495665

SP - 502

EP - 505

BT - International Geoscience and Remote Sensing Symposium (IGARSS)

ER -