Abstract
Abstract Actual land cover maps are a very good source of information on present human activities. It increases value of actual spatial databases and it is a key element for decision makers. Therefore, it is important to develop fast and cheap algorithms and procedures of spatial data updating. Every day, satellite remote sensing deliver vast amount of new data, which can be semi-automatically classified. The paper presents a method of land cover classification based on a fuzzy artificial neural network simulator and Landsat TM satellite images. The latest CORINE Land Cover 2012 polygons were used as reference data. Three satellite images acquired 21 April 2011, 5 June 2010, 27 August 2011 over Warsaw and surrounding areas were processed. As an outcome of classification procedure, the maps, error matrices and a set of overall, producer and user accuracies and a kappa coefficient were achieved. The classification accuracy oscillates around 76% and confirms that artificial neural networks can be successfully used for forest, urban fabric, arable land, pastures, inland waters and permanent crops mapping. Low accuracies were obtained in case of heterogenic land cover units.
Highlights
Development of a current land cover map is a time-consuming procedure, because due to vegetation growth and fast urbanization processes such maps must be frequently updated
Until now Corine Land Cover (CLC) databases for Poland have been created as a result of an expert visual interpretation of satellite images
The article presents the methods of land cover classification according to the Corine Land Cover legend using satellite images from Landsat TM1 and the fuzzy ARTMAP simulator
Summary
Development of a current land cover map is a time-consuming procedure, because due to vegetation growth and fast urbanization processes such maps must be frequently updated. Until now Corine Land Cover (CLC) databases for Poland have been created as a result of an expert visual interpretation of satellite images. It is important that an automatic or semi-automatic methods of land cover mapping are developed Such methods are more objective and less expensive, and the process of classification takes less time than in the case of visual interpretation. The article presents the methods of land cover classification according to the Corine Land Cover legend using satellite images from Landsat TM1 and the fuzzy ARTMAP simulator. M. Heinl et al (2009) compared the outcome of land cover classification performed using artificial neural networks (total accuracy 86%) with the method of maximum likelihood (total accuracy 75%) and discriminant analysis (total accuracy 75%). U. Pytlak (2013), classifying a Landsat satellite image, obtained total accuracy of 91%, and M. Pytlak (2013), classifying a Landsat satellite image, obtained total accuracy of 91%, and M. Kacprzyk (2013), from a Landsat satellite image, obtained a total accuracy of 68%
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
