期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2010
卷号：XXXVIII - 4/C7
出版社：Copernicus Publications
摘要：This study uses the InterIMAGE system and imagery from the QuickBird II optical sensor for the classification of the land cover of two test-sites in the metropolis of S.o Paulo, Brazil. InterIMAGE is an open source and free access framework for knowledge-based image classification. Within InterIMAGE human knowledge is represented as a semantic net and by user-defined rules based on the paradigms of object-oriented image analysis. The Segmentation Parameter Tuner system was used for the search of appropriate segmentation parameters. This system uses a genetic algorithm for the optimization of the parameters. For the description of the land cover classes in terms of features and thresholds, a strategy combining a hierarchical structure of classes and the decision tree algorithm C4.5 was elaborated. The classification model was then formatted according to InterIMAGE's image analysis strategy. The proposed methodology has shown to be efficient for the automatic mapping of the land cover in complex urban areas such as those found in the metropolis of S.o Paulo. The final classification achieved an overall accuracy of 73% and a Kappa Accuracy Index of 0.69. This study has explored the main functionalities of InterIMAGE, presenting its potentialities for object- and knowledge-based image classification
关键词：InterIMAGE System; Knowledge-based Image Classification; Urban Land Cover
