Abstract: Crop area estimation is a key element in crop production forecasting and estimation. Satellite imagery can provide valuable information for stratification purposes and can be used as a source of proxy variables for aposteriori correction of area estimates. In this regard, efficiency of crop area estimation using satellite imagery depends on the accuracy of crop classification. In this paper, we apply optical and SAR satellite imagery for discriminating major crop types in Ukraine. First, we compare efficiency of several optical image types (MODIS, Landsat TM, AWiFS, LISS-III and RapidEye) combined with a field survey on a stratified sample of square segments. Additionally, field data were collected “along the road” as training data for image classification algorithms. The results show particular difficulties in discriminating summer crops in Ukraine such as maize, soy beans, sunflower, sugar beet, using only optical satellite images. Therefore, we incorporate satellite SAR images (RADARSAT-2 quad-polarization) in order to improve discrimination between summer crops. Obtained results show that omission and commission classification errors can be reduced by adding radar imagery to optical ones.

Keywords: remote sensing, agriculture, statistics, estimation.

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

Link:

APPLICATION OF SATELLITE OPTICAL AND SAR IMAGES FOR CROP MAPPING AND EREA ESTIMATION IN UKRAINE

Nataliia Kussul, Sergii Skakun, Oleksii Kravchenko, Andrii Shelestov, Javier Francisco Gallego, Olga Kussul

http://www.foibg.com/ijitk/ijitk-vol07/ijitk07-03-p01.pdf