Open AccessThis article is
- freely available
Object-Based Classification of Ikonos Imagery for Mapping Large-Scale Vegetation Communities in Urban Areas
Spatial Ecology Research Facility, School of Surveying, University of Otago, PO Box 56, Dunedin, New Zealand
Earth Observation Research Group, Natural Resources & Environment, CSIR, PO Box 395, Pretoria 0001, South Africa
Centre for Advanced Computational Solutions, Lincoln University, PO Box 84, Lincoln, New Zealand
* 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 landcover products. Detailed habitat maps are created by manual interpretation of aerialphotographs, but this is time consuming and costly at large scale. To address this issue, wetested the effectiveness of object-based classifications that use automated imagesegmentation to extract meaningful ground features from imagery. We applied thesetechniques to very high resolution multispectral Ikonos images to produce vegetationcommunity maps in Dunedin City, New Zealand. An Ikonos image was orthorectified and amulti-scale segmentation algorithm used to produce a hierarchical network of image objects.The upper level included four coarse strata: industrial/commercial (commercial buildings),residential (houses and backyard private gardens), vegetation (vegetation patches larger than0.8/1ha), and water. We focused on the vegetation stratum that was segmented at moredetailed level to extract and classify fifteen classes of vegetation communities. The firstclassification yielded a moderate overall classification accuracy (64%, κ = 0.52), which ledus to consider a simplified classification with ten vegetation classes. The overallclassification accuracy from the simplified classification was 77% with a κ value close tothe excellent range (κ = 0.74). These results compared favourably with similar studies inother environments. We conclude that this approach does not provide maps as detailed as those produced by manually interpreting aerial photographs, but it can still extract ecologically significant classes. It is an efficient way to generate accurate and detailed maps in significantly shorter time. The final map accuracy could be improved by integrating segmentation, automated and manual classification in the mapping process, especially when considering important vegetation classes with limited spectral contrast.
Keywords: object-based classification; remote sensing; cities; New Zealand; biodiversity; habitat.
Article StatisticsClick here to load and display the download statistics.
Notes: Multiple requests from the same IP address are counted as one view.
Cite This Article
MDPI and ACS Style
Mathieu, R.; Aryal, J.; Chong, A.K. Object-Based Classification of Ikonos Imagery for Mapping Large-Scale Vegetation Communities in Urban Areas. Sensors 2007, 7, 2860-2880.
Mathieu R, Aryal J, Chong AK. Object-Based Classification of Ikonos Imagery for Mapping Large-Scale Vegetation Communities in Urban Areas. Sensors. 2007; 7(11):2860-2880.
Mathieu, Renaud; Aryal, Jagannath; Chong, Albert K. 2007. "Object-Based Classification of Ikonos Imagery for Mapping Large-Scale Vegetation Communities in Urban Areas." Sensors 7, no. 11: 2860-2880.