File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Assessment of some small window-based spatial features for land-cover classification

TitleAssessment of some small window-based spatial features for land-cover classification
Authors
Gong, PengHowarth, Philip J.
Issue Date1993
Citation
International Geoscience and Remote Sensing Symposium (IGARSS), 1993, v. 4, p. 1668-1670 How to Cite?
DOI: http://dx.doi.org/10.1109/IGARSS.1993.322063
AbstractFourteen small (3×3) window-based spatial measures are applied to a SPOT HRV multispectral Band 3 image to extract spatial features for the rural-urban fringe of Metropolitan Toronto, Canada. The spatial features are combined with the original image to identify 12 land-cover classes. Four classifiers were used in the study. Results show that when nine of the spatial features are in turn combined with the three original images, significantly improved classification accuracies (at the 95 percent confidence level) are obtained compared with using only the multispectral information from the three original images.
Persistent Identifierhttp://hdl.handle.net/10722/296505

 

DC FieldValueLanguage
dc.contributor.authorGong, Peng-
dc.contributor.authorHowarth, Philip J.-
dc.date.accessioned2021-02-25T15:16:03Z-
dc.date.available2021-02-25T15:16:03Z-
dc.date.issued1993-
dc.identifier.citationInternational Geoscience and Remote Sensing Symposium (IGARSS), 1993, v. 4, p. 1668-1670-
dc.identifier.urihttp://hdl.handle.net/10722/296505-
dc.description.abstractFourteen small (3×3) window-based spatial measures are applied to a SPOT HRV multispectral Band 3 image to extract spatial features for the rural-urban fringe of Metropolitan Toronto, Canada. The spatial features are combined with the original image to identify 12 land-cover classes. Four classifiers were used in the study. Results show that when nine of the spatial features are in turn combined with the three original images, significantly improved classification accuracies (at the 95 percent confidence level) are obtained compared with using only the multispectral information from the three original images.-
dc.languageeng-
dc.relation.ispartofInternational Geoscience and Remote Sensing Symposium (IGARSS)-
dc.titleAssessment of some small window-based spatial features for land-cover classification-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/IGARSS.1993.322063-
dc.identifier.scopuseid_2-s2.0-0027837053-
dc.identifier.volume4-
dc.identifier.spage1668-
dc.identifier.epage1670-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats