Knowledge-based land use classification from IKONOS imagery for Arkadi, Crete, Greece

Argialas, DP; Goudoula, V

dc.contributor.author	Argialas, DP	en
dc.contributor.author	Goudoula, V	en
dc.date.accessioned	2014-03-01T02:49:14Z
dc.date.available	2014-03-01T02:49:14Z
dc.date.issued	2002	en
dc.identifier.issn	0277786X	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/34432
dc.subject	Classification features	en
dc.subject	ERDAS IMAGINE	en
dc.subject	Expert system	en
dc.subject	Hierarchical classification	en
dc.subject	Rule-based classification	en
dc.subject	Spatial model	en
dc.subject.other	Color image processing	en
dc.subject.other	Decision theory	en
dc.subject.other	Imaging systems	en
dc.subject.other	Land use	en
dc.subject.other	Maximum likelihood estimation	en
dc.subject.other	Object recognition	en
dc.subject.other	Photointerpretation	en
dc.subject.other	Statistical methods	en
dc.subject.other	Vegetation	en
dc.subject.other	Digital terrain model	en
dc.subject.other	Expert Classifier model	en
dc.subject.other	Hierarchical classification	en
dc.subject.other	Rule-based classification	en
dc.subject.other	Expert systems	en
dc.title	Knowledge-based land use classification from IKONOS imagery for Arkadi, Crete, Greece	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1117/12.463282	en
heal.identifier.secondary	http://dx.doi.org/10.1117/12.463282	en
heal.publicationDate	2002	en
heal.abstract	The objective of the present research effort was the investigation of expert system classification techniques for land use mapping from very high resolution images for a typical Greek landscape. Data used included an IKONOS image of the Arkadi area in Crete acquired on September 2000, and a digital terrain model. Photointerpretation was carried out using color composites, band ratios and maps of scale 1:5.000 and 1:50.000. Maximum likelihood was used for per pixel supervised classification and its accuracy was 72%. A knowledge base containing 51 rules, 44 hypotheses and 12 variables was developed in the Expert Classifier module of ERDAS Imagine. A hierarchical organization of thematic classes was developed in four levels through photointerpretation and study of the spectral reflectance diagrams and thematic class histograms. The image was first classified into three general categories: water-like, vegetation-like and soil-like materials. These were then separated into sub-classes. Classification rules were enriched with ancillary data such as the slopes, the road network, the NDVI vegetation index, the results of a spatial model computing texture, and indices reflecting the polygon shape and perimeter. Overall accuracy of the classification with the expert system was 82%.	en
heal.journalName	Proceedings of SPIE - The International Society for Optical Engineering	en
dc.identifier.doi	10.1117/12.463282	en
dc.identifier.volume	4886	en
dc.identifier.spage	193	en
dc.identifier.epage	204	en