617
Views
64
CrossRef citations to date
0
Altmetric
Methods, Models, and GIS

Using Geometrical, Textural, and Contextual Information of Land Parcels for Classification of Detailed Urban Land Use

, , &
Pages 76-98 | Received 01 Feb 2007, Accepted 01 Mar 2008, Published online: 23 Dec 2008
 

Abstract

Detailed urban land use data are important to government officials, researchers, and businesspeople for a variety of purposes. This article presents an approach to classifying detailed urban land use based on geometrical, textural, and contextual information of land parcels. An area of 6 by 14 km in Austin, Texas, with land parcel boundaries delineated by the Travis Central Appraisal District of Travis County, Texas, is tested for the approach. We derive fifty parcel attributes from relevant geographic information system (GIS) and remote sensing data and use them to discriminate among nine urban land uses: single family, multifamily, commercial, office, industrial, civic, open space, transportation, and undeveloped. Half of the 33,025 parcels in the study area are used as training data for land use classification and the other half are used as testing data for accuracy assessment. The best result with a decision tree classification algorithm has an overall accuracy of 96 percent and a kappa coefficient of 0.78, and two naive, baseline models based on the majority rule and the spatial autocorrelation rule have overall accuracy of 89 percent and 79 percent, respectively. The algorithm is relatively good at classifying single-family, multifamily, commercial, open space, and undeveloped land uses and relatively poor at classifying office, industrial, civic, and transportation land uses. The most important attributes for land use classification are the geometrical attributes, particularly those related to building areas. Next are the contextual attributes, particularly those relevant to the spatial relationship between buildings, then the textural attributes, particularly the semivariance texture statistic from 0.61-m resolution images.

Para una variedad de propósitos, los datos detallados sobre uso del suelo urbano son importantes para agentes gubernamentales, investigadores y hombres de negocios, Este artículo presenta un enfoque para clasificar en detalle los usos del suelo urbano, a partir de información geométrica, textural y contextual de las parcelas. Este enfoque se puso a prueba en un área de 6 X 14 km, en Austin, Texas, con los linderos de las parcelas delineados por el Distrito Central de Avalúos Travis, del condado Travis. Con datos relevantes generados por un sistema de información geográfica (SIG) y por teledetección, derivamos cincuenta atributos de las parcelas que se utilizaron para discriminar entre nueve usos del suelo urbano: familiar, multifamiliar, comercial, oficinas, industria, cívico, espacio abierto, transporte y no desarrollado. La mitad de las 33.025 parcelas del área de estudio fungió como espacio de datos para entrenamiento en la clasificación del uso del suelo, y la otra mitad como campo de datos para prueba para efectos de la exactitud en la evaluación. El mejor resultado logrado con un algoritmo clasificatorio por árbol de decisiones tiene una exactitud general del 96 por ciento y un coeficiente kappa de 0.78, y dos modelos de línea de base basados el uno en la regla de la mayoría y el otro en la regla de la autocorrelación espacial, tienen exactitudes totales de 89 y 79 por ciento, respectivamente. El algoritmo es relativamente bueno en lo que concierne a la clasificación de los usos del suelo unifamiliar, multifamiliar, comercial, espacio abierto y usos no desarrollados, y relativamente deficiente en cuanto a la clasificación de usos del suelo para oficinas, industria, cívico y transporte. Los atributos más importantes para la clasificación del uso del suelo son los atributos geométricos, en particular aquellos relacionados con áreas de edificios. Luego vienen los atributos contextuales, particularmente los relevantes a las relaciones espaciales entre los edificios; después los atributos texturales, en particular la estadística de semivarianza de textura de imágenes de 0.61-m de resolución.

Acknowledgments

While this article was being written, Shuo-Sheng Wu was supported by a post-doctoral fellowship sponsored by the United States Geological Survey (USGS) Center of Excellence for Geospatial Information Science (CEGIS) through University Consortium for Geographic Information Science (UCGIS). The authors would like to thank the three anonymous reviewers and the editor, Mei-Po Kwan, who provided constructive comments that greatly improved this article from its original form.

Notes

1. Grandfathering is the practice of exempting current rights holders from a new regulation or legal qualification.

2. For computational convenience, all parcel attributes are rescaled to a value between 0 and 65,535 (unsigned sixteen bit) before transforming to pixel values.

3. The standard deviation of this parcel attribute for transportation land use is indeed the highest among all land use classes. See CitationWu, Silván-Cárdenas, and Wang (2007) for details.

Log in via your institution

Log in to Taylor & Francis Online

PDF download + Online access

  • 48 hours access to article PDF & online version
  • Article PDF can be downloaded
  • Article PDF can be printed
USD 53.00 Add to cart

Issue Purchase

  • 30 days online access to complete issue
  • Article PDFs can be downloaded
  • Article PDFs can be printed
USD 312.00 Add to cart

* Local tax will be added as applicable

Related Research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.