A Hybrid Approach to Land Cover Classification from Multi Spectral Images
This work is part of a wider project whose general objective is to develop a methodology for the automatic classification, based on CORINE land-cover (CLC) classes, of high resolution multispectral IKONOS images. The specific objective of this paper is to describe a new methodology for producing really exploitable results from automatic classification algorithms. Input data are basically constituted by multispectral images, integrated with textural and contextual measures. The output is constituted by an image with each pixel assigned to one out of 15 classes at the second level of the CLC legend or let unclassified (somehow a better solution than a classification error), plus a stability map that helps users to separate the regions classified with high accuracy from those whose classification result should be verified before being used.
KeywordsLand cover - land use (LCLU) multispectral images pixel-based and object-based classification AdaBoost stability map
- 1.Ball, J.E., Bruce, L.M.: Level set segmentation of remotely sensed hyperspectral images. In: Proceedings of Int. Geoscience and Remote Sensing Symposium, vol. 8, pp. 5638–5642Google Scholar
- 2.European Environment Agency (EEA), CLC 2006 technical guidelines - Technical report, http://www.eea.europa.eu/publications/technical_report_2007_17
- 8.Sutton, C.D.: Handbook of Statistics, vol. 24, cap. 11: Classification and regression trees, bagging, and boosting. Elsevier, Amsterdam (2005)Google Scholar
- 12.Yu, Y.W., Wang, J.H.: Image segmentation based on region growing and edge detection. In: Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, vol. 6, pp. 798–803 (1999)Google Scholar
- 13.Yuan, F., Bauer, M.E.: Mapping impervious surface area using high resolution imagery: A comarison of object-based and per pixel classification. In: Proceedings of ASPRS 2006 (2006)Google Scholar