object-based classification of ikonos imagery for mapping large-scale vegetation communities in urban areas基于对象分类的ikonos图像映射大规模植被社区在城市地区.pdfVIP

Sensors 2007, 7, 2860-2880 sensors ISSN 1424-8220 © 2007 by MDPI /sensors Full Research Paper Object-Based Classification of Ikonos Imagery for Mapping Large-Scale Vegetation Communities in Urban Areas Renaud Mathieu 1, 2,* Jagannath Aryal 3 and Albert K. Chong 1 1 Spatial Ecology Research Facility, School of Surveying, University of Otago, PO Box 56, Dunedin, New Zealand; E-mail: renaud.mathieu@stonebow.otago.ac.nz 2 Earth Observation Research Group, Natural Resources Environment, CSIR, PO Box 395, Pretoria 0001, South Africa; E-mail: rmathieu@csir.co.za 3 Centre for Advanced Computational Solutions, Lincoln University, PO Box 84, Lincoln, New Zealand; E-mail: aryalj@lincoln.ac.nz * Author to whom correspondence should be addressed. Received: 13 September 2007 / Accepted: 19 November 2007 / Published: 20 November 2007 Abstract: Effective assessment of biodiversity in cities requires detailed vegetation maps. To date, most remote sensing of urban vegetation has focused on thematically coarse land cover products. Detailed habitat maps are created by manual interpretation of aerial photographs, but this is time consuming and costly at large scale. To address this issue, we tested the effectiveness of object-based classifications that use automated image segmentation to extract meaningful ground features from imagery. We applied these techniques to very high resolution multispectral Ikonos images to produce vegetation community maps in Dunedin