Remote sensing for urban planning and management: The use of window-independent context segmentation to extract urban features in Stockholm. (July 2015)

• Record Type: Journal Article
• Authors: Nielsen, Michael Meinild
• Is Part Of: Computers, environment and urban systems. Volume 52(2015)
• Page Start: 1
• Page End: 9
• Publication Date: 2015-07
• Subjects: Urban remote sensing -- Segmentation -- Spatial analysis -- Urban planning and management -- Feature extraction; City planning -- Data processing -- Periodicals; Regional planning -- Data processing -- Periodicals; 303.4834
• DOI: 10.1016/j.compenvurbsys.2015.02.002
• Languages: English
• ISSNs: 0198-9715

Abstract

Highlights: Tests a novel method's ability to extract information relevant for urban analysis. The method is shown to extract areas that differ in function and underlying planning theories and practices. The method is put into a theoretical framework. Abstract: The strategic scale of urban planning and management is concerned with the planning and monitoring of general land use in a city, such as different types of residential, industrial and commercial areas. Because of the poor results of standard per-pixel-based classification methods in urban areas, visual interpretation of remote sensing data is often preferred. This paper empirically tests the ability of a novel method, called window-independent context segmentation, to extract information that is useful at the strategic scale of urban planning and management. The method is implemented in a theoretical framework that is a response to Bibby and Shepherd's call for a new ontology in the application of geographic information systems and remote sensing to land use issues. In a case study using a SPOT5 satellite image of central Stockholm, the window-independent context segmentation method extracts urban features that correspond to the strategic scale of urban-planning and management and that differ in function and underlying planning theory and practice.