Super-resolution mapping of landscape objects from coarse spatial resolution imagery

Anuar Mikdad Muad, G. M. Foody

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

1 Citation (Scopus)

Abstract

The landscape patches that are fundamental to landscape ecology may be considered as objects to be extracted from remotely sensed imagery. The accuracy with which objects may be characterised varies as a function of the spatial resolution of the imagery used. In general terms, a coarsening of the spatial resolution degrades the characterization of objects, notably through an increase in the proportion of mixed pixels which cannot be appropriately represented by conventional hard classification techniques. Accurate landscape mapping may often require either the adoption of fine spatial resolution imagery or use of sub-pixel scale analyses of coarse spatial resolution imagery. As the former is often impractical, the full realization of the potential of remote sensing as a source of information on landscape objects requires developments in sub-pixel scale techniques. In this paper, a new method of super-resolution mapping based on a unifying framework of image halftoning, inverse halftoning and Hopfield neural network techniques is proposed as a means of gaining accurate information on landscape patches from coarse spatial resolution images. Fine temporal resolution of coarse spatial resolution remote sensing systems is exploited by fusing the time-series data as an input for the super-resolution mapping. The accuracy of the analyses is evaluated relative to conventional a hard classification technique using object characterization. The results show that the proposed hybrid method is considerably more accurate than standard hard analyses in estimating the shape of the objects. The results also demonstrate that objects that are smaller than a pixel, which are missed using the hard classification techniques, can be detected using the super-resolution mapping.

Original languageEnglish
Title of host publicationInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
PublisherInternational Society for Photogrammetry and Remote Sensing
Volume38
Edition4C7
Publication statusPublished - 2010
Externally publishedYes
EventGeographic Object-Based Image Analysis, GEOBIA 2010 - Ghent, Belgium
Duration: 29 Jun 20102 Jul 2010

Other

OtherGeographic Object-Based Image Analysis, GEOBIA 2010
CountryBelgium
CityGhent
Period29/6/102/7/10

Fingerprint

spatial resolution
imagery
Pixels
Optical resolving power
pixel
Remote sensing
Hopfield neural networks
Coarsening
Ecology
Image resolution
remote sensing
Time series
landscape ecology
General Terms
source of information
neural network
time series
ecology
method

Keywords

  • Coarse spatial resolution image
  • Landscape patches characterization
  • Super-resolution mapping

ASJC Scopus subject areas

  • Information Systems
  • Geography, Planning and Development

Cite this

Muad, A. M., & Foody, G. M. (2010). Super-resolution mapping of landscape objects from coarse spatial resolution imagery. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives (4C7 ed., Vol. 38). International Society for Photogrammetry and Remote Sensing.

Super-resolution mapping of landscape objects from coarse spatial resolution imagery. / Muad, Anuar Mikdad; Foody, G. M.

International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. Vol. 38 4C7. ed. International Society for Photogrammetry and Remote Sensing, 2010.

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

Muad, AM & Foody, GM 2010, Super-resolution mapping of landscape objects from coarse spatial resolution imagery. in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 4C7 edn, vol. 38, International Society for Photogrammetry and Remote Sensing, Geographic Object-Based Image Analysis, GEOBIA 2010, Ghent, Belgium, 29/6/10.
Muad AM, Foody GM. Super-resolution mapping of landscape objects from coarse spatial resolution imagery. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 4C7 ed. Vol. 38. International Society for Photogrammetry and Remote Sensing. 2010
Muad, Anuar Mikdad ; Foody, G. M. / Super-resolution mapping of landscape objects from coarse spatial resolution imagery. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. Vol. 38 4C7. ed. International Society for Photogrammetry and Remote Sensing, 2010.
@inproceedings{a27e07361a354dc6a9591cc9cedc33ed,
title = "Super-resolution mapping of landscape objects from coarse spatial resolution imagery",
abstract = "The landscape patches that are fundamental to landscape ecology may be considered as objects to be extracted from remotely sensed imagery. The accuracy with which objects may be characterised varies as a function of the spatial resolution of the imagery used. In general terms, a coarsening of the spatial resolution degrades the characterization of objects, notably through an increase in the proportion of mixed pixels which cannot be appropriately represented by conventional hard classification techniques. Accurate landscape mapping may often require either the adoption of fine spatial resolution imagery or use of sub-pixel scale analyses of coarse spatial resolution imagery. As the former is often impractical, the full realization of the potential of remote sensing as a source of information on landscape objects requires developments in sub-pixel scale techniques. In this paper, a new method of super-resolution mapping based on a unifying framework of image halftoning, inverse halftoning and Hopfield neural network techniques is proposed as a means of gaining accurate information on landscape patches from coarse spatial resolution images. Fine temporal resolution of coarse spatial resolution remote sensing systems is exploited by fusing the time-series data as an input for the super-resolution mapping. The accuracy of the analyses is evaluated relative to conventional a hard classification technique using object characterization. The results show that the proposed hybrid method is considerably more accurate than standard hard analyses in estimating the shape of the objects. The results also demonstrate that objects that are smaller than a pixel, which are missed using the hard classification techniques, can be detected using the super-resolution mapping.",
keywords = "Coarse spatial resolution image, Landscape patches characterization, Super-resolution mapping",
author = "Muad, {Anuar Mikdad} and Foody, {G. M.}",
year = "2010",
language = "English",
volume = "38",
booktitle = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
publisher = "International Society for Photogrammetry and Remote Sensing",
edition = "4C7",

}

TY - GEN

T1 - Super-resolution mapping of landscape objects from coarse spatial resolution imagery

AU - Muad, Anuar Mikdad

AU - Foody, G. M.

PY - 2010

Y1 - 2010

N2 - The landscape patches that are fundamental to landscape ecology may be considered as objects to be extracted from remotely sensed imagery. The accuracy with which objects may be characterised varies as a function of the spatial resolution of the imagery used. In general terms, a coarsening of the spatial resolution degrades the characterization of objects, notably through an increase in the proportion of mixed pixels which cannot be appropriately represented by conventional hard classification techniques. Accurate landscape mapping may often require either the adoption of fine spatial resolution imagery or use of sub-pixel scale analyses of coarse spatial resolution imagery. As the former is often impractical, the full realization of the potential of remote sensing as a source of information on landscape objects requires developments in sub-pixel scale techniques. In this paper, a new method of super-resolution mapping based on a unifying framework of image halftoning, inverse halftoning and Hopfield neural network techniques is proposed as a means of gaining accurate information on landscape patches from coarse spatial resolution images. Fine temporal resolution of coarse spatial resolution remote sensing systems is exploited by fusing the time-series data as an input for the super-resolution mapping. The accuracy of the analyses is evaluated relative to conventional a hard classification technique using object characterization. The results show that the proposed hybrid method is considerably more accurate than standard hard analyses in estimating the shape of the objects. The results also demonstrate that objects that are smaller than a pixel, which are missed using the hard classification techniques, can be detected using the super-resolution mapping.

AB - The landscape patches that are fundamental to landscape ecology may be considered as objects to be extracted from remotely sensed imagery. The accuracy with which objects may be characterised varies as a function of the spatial resolution of the imagery used. In general terms, a coarsening of the spatial resolution degrades the characterization of objects, notably through an increase in the proportion of mixed pixels which cannot be appropriately represented by conventional hard classification techniques. Accurate landscape mapping may often require either the adoption of fine spatial resolution imagery or use of sub-pixel scale analyses of coarse spatial resolution imagery. As the former is often impractical, the full realization of the potential of remote sensing as a source of information on landscape objects requires developments in sub-pixel scale techniques. In this paper, a new method of super-resolution mapping based on a unifying framework of image halftoning, inverse halftoning and Hopfield neural network techniques is proposed as a means of gaining accurate information on landscape patches from coarse spatial resolution images. Fine temporal resolution of coarse spatial resolution remote sensing systems is exploited by fusing the time-series data as an input for the super-resolution mapping. The accuracy of the analyses is evaluated relative to conventional a hard classification technique using object characterization. The results show that the proposed hybrid method is considerably more accurate than standard hard analyses in estimating the shape of the objects. The results also demonstrate that objects that are smaller than a pixel, which are missed using the hard classification techniques, can be detected using the super-resolution mapping.

KW - Coarse spatial resolution image

KW - Landscape patches characterization

KW - Super-resolution mapping

UR - http://www.scopus.com/inward/record.url?scp=84923950843&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923950843&partnerID=8YFLogxK

M3 - Conference contribution

VL - 38

BT - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

PB - International Society for Photogrammetry and Remote Sensing

ER -