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-4-8-2/W9
页码：40-45
出版社：Copernicus Publications
摘要：The results obtained after the application of parcel-oriented classification over two geographic areas of Galicia, in the northwest of Spain, are presented. In this region, forest and shrublands in mountain environments are very heterogeneous, with many private unproductive parcels, some of which are in a high state of abandonment. This situation entails a low economic productivity of the land and a higher vulnerability to wildfires and degradation in the affected areas. In this sense, the local government is promoting new methodologies based on high resolution images in order to classify the territory in basic and generic land uses. This land database will be used to plan specific actions for the sustainable management of degraded parcels, including the creation of a land bank. The data used were 0.5 m/pixel visible and near infrared aerial imagery, and cadastral cartography employed to define the image objects (parcels) to be analysed. A set of features was computed from the images to quantitative describe different properties of the objects: spectral, texture and structural. In addition, several shape features were extracted from the parcel polygons. The classification was performed by means of decision trees, combined using the boosting technique. For the evaluation, field data samples were collected. An additional test using as a descriptive feature the land use class contained in a previous thematic database was performed. The overall accuracies of the classifications obtained are always above 90%. In one of the two areas tested, where forest and shrublands are especially undefined, the discrimination between these two classes is low. In conclusion, the use of automatic parcel-oriented classification techniques for land use updating tasks, particularly when broad and well defined classes are required, seems to be effective in some of the areas tested
关键词：Object-oriented classification; decision trees; high-resolution imagery; land cover; mapping; land bank
