A procedure for semi-automated cadastral boundary feature extraction from high-resolution satellite imagery

• Published in: Journal of spatial science Vol. 63; no. 1; pp. 75 - 92
• Main Authors: Wassie, Y. A., Koeva, M. N., Bennett, R. M., Lemmen, C. H. J.
• Format: Journal Article
• Language: English
• Published: Taylor & Francis 02.01.2018
• Subjects: boundary mapping; Cadastre; feature extraction; fit for purpose; mean-shift segmentation; QGIS; satellite imagery; semi-automatic
• ISSN: 1449-8596; 1836-5655
• DOI: 10.1080/14498596.2017.1345667

Fit-for-purpose land administration aims to align cadastral policies, administration and technology selection with the prevailing societal needs and capacity within a country context. It seeks to support delivery of more rapid and low-cost cadastral boundary mapping - and ultimately more widespread land tenure security. The philosophy suggests that when high positional accuracies are not the primary concern, but when time pressure is, high-resolution satellite images can serve as a source for creating cadastral boundary information. This paper explores the potential of mean-shift segmentation plug-in in QGIS to semi-automatically extract cadastral boundaries in rural areas - based on the land cover information from WorldView-2 satellite images. The segmentation gives a vector file satisfying many cadastral boundary requirements and ready to be used in a GIS environment. The buffer overlay method was used to assess the quality of extracted boundaries. For a non-vegetated terrain having visible boundaries, the approach could be taken as an alternative to support existing, relatively slow, boundary mapping approaches by minimizing the effects of manual digitization and surveying.