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：The PIMAR Project - Program for Monitoring the Atlantic Rainforest Environment and Urban Growth of Rio de Janeir o through Remote Sensing, aims at the develop ment of an operational methodology for monitoring the land cover dynamics on the borders between Atlantic rainforest remnant areas and urban areas in the city of Rio de Janeiro, Brazil. The project will aid the Government of Rio de Janeiro State in the implementation of actions against aggressions to those forested areas and in the def inition of urban development and environmental planning policies. The basic input for the methodology is a sequence of stereo pairs of IKONOS images, from which both the vertical and horizontal growth of urban areas are being measured by visual interpretation on a multi- temporal basis. The PIMAR Project is currently evaluating the use of an automatic classification model as a way to accelerate land cover change information production to support decision making. This paper presents the first results obtained when applying the prototype of the model in the project's test-site. Such classification model has been developed and tested within the Inter IMAGE system, which is an open-source knowledge and object-based classification system. The automatic classification model is being elaborated considering that an user would have only to collect samples of every land cover class to have, after running the model, the land cover map delivered. The presented prototype model uses the C4.5 algorithm, commonly used spectral features and a simple semantic net for performing the land cover classification of the test-site. The visual analysis and the global and per-class accuracy indexes suggest that the automatically made classification is satisfactorily accurate and has potential for significantly reduce the photo-interpreters work. A Global Accuracy of 81% was obtained as well as a Kappa Index of 0.61. Important classes Vegetated Areas and Urban areas achieved above 75% user and producer's accuracies
关键词：Land Cover Classification; Rainforest Monitoring; Object-Based Image Analysis; Inter IMAGE System
