Classifying rural land-use using multi-feature approach for national land-use survey

摘要

This study put forward a standardize classification model which can meet the requirement of rural land use survey and be suitable for large-scale promotion at the same time, but not merely the research limited in the experiment lab.. In this processing, the land cover classification may adopt the mutli-feature image classification method as followed. Firstly, a class scheme was defined. Then, some suitable features were selected, and every subclass was characterized with a unique combination of these features, in which landscape pattern parameter is one of essential features in consideration. Landscape pattern parameters can treat surface features and its distribution as integration and synthesis, which would help much to the classification. Using these features, image could be recognized and classified easily. Lastly, verify the precision and accuracy of the classification model. By using this classification method, classification accuracy can be improved, and the classification results were easier interpreted when compared with the conventional classification method.