Abstract: This paper presents first results of the use of optical and synthetic-aperture radar (SAR) satellite images to crop classification in Ukraine. The study aims at optimizing SAR parameters to provide timely and economically efficient crop maps/area estimates for Ukrainian landscape. Integration of EO-1 and RADARSAT-2 is done for crop classification using support vector machine (SVM). Classification is carried out per-field. The results on using SAR data for summer crops classification look very promising enabling classification of major summer crops with 10-15% of commission and omission errors under a typical Ukrainian landscape.

Keywords: crop classification, SVM, satellite images, SAR multipolarization.

ACM Classification Keywords: I.4.8 Image Processing and Computer Vision Scene Analysis - Sensor Fusion.

Link:

CROP CLASSIFICATION IN UKRAINE USING SATELLITE OPTICAL AND SAR IMAGES

Nataliia Kussul, Sergii Skakun, Andrii Shelestov, Oleksii Kravchenko, Olga Kussul

http://www.foibg.com/ijima/vol02/ijima02-02-p03.pdf