Opportunities and limitations of object based image analysis for detecting urban impervious and vegetated surfaces using
Monitoring soil sealing in urban environments is of great interest as a key indicator of sustainable land use. Many studies have attempted to automatically classify surface impermeability by using satellite or aerial imagery. Air photo interpretation (API
- PDF / 1,582,777 Bytes
- 15 Pages / 439.37 x 666.142 pts Page_size
- 16 Downloads / 170 Views
M. Kampouraki, G. A. Wood, T. R. Brewer School of Applied Sciences, Department of Natural Resources, Cranfield University, Bedfordshire, MK43 0AL, UK (m.kampouraki.s04, g.a.wood, t.brewer)@cranfield.ac.uk
KEYWORDS: Object, Classification, Urban, Mapping, Remote sensing ABSTRACT: Monitoring soil sealing in urban environments is of great interest as a key indicator of sustainable land use. Many studies have attempted to automatically classify surface impermeability by using satellite or aerial imagery. Air photo interpretation (API) has been used as a method to verify their accuracy. However, independent accuracy assessments of API have not been widely reported. The aims of this research are, firstly, to investigate independent accuracy assessments of API. Secondly, to determine whether object-based image analysis could replace manual interpretation for the detection of sealed soil and vegetated surfaces at the residential garden plot level. Four study areas, representing the industrial, commercial and residential parts of Cambridge, UK were manually digitised and classified by API. The same areas were automatically segmented and manually classified with the use of eCognition. The two methods were compared and the average overall mapping agreement was estimated to be 92%. The disagreement was qualitatively analysed and the advantages and disadvantages of each method were discussed. The very high agreement between the two methods in conjunction with the benefits of the automated method led to the conclusion that automated segmentation using eCognition could replace the manual boundary delineation when true-colour aerial
556
M. Kampouraki, G. A. Wood, T. R. Brewer
photography is used. Future work will examine automated image classification methods, using eCognition, as a replacement for normal image interpretation methods.
1 Introduction Urban development presents the greatest driver of soil loss due to sealingover by buildings, pavement and transport infrastructure. Soil sealing is recognised as one of the major threats to soil. The ability to monitor the rates, types and geo-spatial distribution of soil sealing is crucial to understanding the severity of pressure on soils and their impact on European and global socio-economic and environmental systems (Wood et al., 2006).
1.1 Monitoring soil sealing by remote sensing There are few internationally recognised definitions of soil sealing (Burghardt et al. 2004). The European Union accepts that “soil sealing refers to changing the nature of a soil such that it behaves as an impermeable medium and describes the covering or sealing of the soil surface by impervious materials” (EEA glossary 2006). Remotely sensed data cannot directly measure whether a surface is permeable but it can monitor cover types (e.g. concrete or tarmac) and infer permeability. Grenzdörffer (2005) categorised sealed areas simply as either built-up or non-built-up areas. Arguably, the most detailed mapping of soil sealing was carried by the Office for Urban Drainage Systems in Dresden, Germany.
Data Loading...
