In order to obtain urban distribution, the decision tree classification technology is used to classify remote sensing image in the study area. Landsat TM image ,digital elevation model (DEM), and normalized water index, vegetation index and cultivated land index as well as image spectral statistical characteristics and space information characteristics are used.Through the threshold determination methods, decision tree is built to achieve a classification of six kinds of objects in the study area ,which are water body, artificial structure, bare land, cultivated land, forest land and grassland. Finally confusion matrix is used to evaluate classification results, the overall classification accuracy of the decision tree is 89.52%, the Kappa coefficient is 0.867.
The research and application of medium resolution remote sensing images in the city information extraction
Selected Papers from Conferences of the Photoelectronic Technology Committee of the Chinese Society of Astronautics: Optical Imaging, Remote Sensing, and Laser-Matter Interaction 2013 ; 2013 ; SuZhou,China
Proc. SPIE ; 9142
2014-02-21
Conference paper
Electronic Resource
English
British Library Conference Proceedings | 2014
|Object and Topology Extraction from Remote Sensing Images
British Library Conference Proceedings | 2005
|Research on Vehicle Information Extraction from High-Resolution Satellite Images
British Library Conference Proceedings | 2009
|