CONSTRUCTION OF DECISION REGION BORDERS BY GEOMETRIC MODELLING OF TRAINING SETS Application to land cover classes in remotely sensed images
نویسندگان
چکیده
In this paper a novel methodology to construct decision region borders that geometrically models the training sets of points is presented. It is shown that with the incorporation of the features of the training sets more correct decision borders are designed and, in consequence, higher classification rates are obtained. This methodology is completely based on mathematical morphology operators and is illustrated with two features (wetness’ tasselled cap and NDV I’s vegetation index) of seven land cover classes (forest (3), soil (2), vegetation and water) constructed from remotely sensed images of a region in centre Portugal.
منابع مشابه
Spatiotemporal analysis of remotely sensed Landsat time series data for monitoring 32 years of urbanization
The world is witnessing a dramatic shift of settlement pattern from rural to urban population, particularly in developing countries. The rapid Addis Ababa urbanization reflects this global phenomenon and the subsequent socio-economic and environmental impacts, are causing massive public uproar and political instability. The objective of this study was to use remotely sensed Landsat data to iden...
متن کاملImprovement of Image Classification with the Integration of Topographical Data
Remotely sensed data are essentially used for land cover and vegetation classification. However, classes of interest are often imperfectly separable in the feature space provided by the spectral data. One of the most common attempts to improve image classification is the integration of ancillary data into classification. In this study, an approach for integrating topographic data into land cove...
متن کاملImproving Classification Rates by Modelling the Clusters of Trainings Sets in Features Space Using Mathematical Morphology Operators
The exploration of the features presented by the training sets of each class (size, shape and orientation) in order to construct the respective decision regions borders without making explicitly any statistical hypothesis is presented in this paper. Its incorporation allows defining more correct decision borders since there is a significant improvement in the classification rates obtained. Math...
متن کاملApplication of remote sensing and geographical information system in mapping land cover of the national park
The study was conducted with the objective of mapping landscape cover of Nechsar National park in Ethiopia to produce spatially accurate and timely information on land use and changing pattern. Monitoring provides the planners and decision-makers with required information about the current state of its development and the nature of changes that have occurred. Remote sensing and Geographical Inf...
متن کاملUrban Land Use Classes with Fuzzy Membership and Classification Based on Integration of Remote Sensing and Gis
Urban land use classification from remotely sensed images has drawn great attention in the past decades. Most researchers derive land use data from remotely sensed images alone, but the results are not quite satisfying for detecting detailed land use classes in urban areas. Fuzzy urban land use classes proposed here consist of a number of fuzzy memberships that offer direct links to findings fr...
متن کامل