Crops planting information extraction based on multi-temporal remote sensing images

The multi-temporal remote sensing data were used to extract crops planting information quickly and accurately from TM/ETM+ remote sensing images and thirteen MODIS time series remote sensing images, together with the supervised classification and decision tree classification system to interpret major crops in the Heilonggang area. Overall, classification accuracy was up to 91.3%. Compared with one simple supervised classification of TM images, the relative errors of cotton, maize, wheat and vegetables reduced by 1.3%, 20.5%, 2.0% and 13.8% respectively. It proved that this method has high accuracy and it is a good index for the crop planting distribution. The data can provide important scientific information for the adjustment of the major crops planting structure in Heilonggang area and application references for crops classification and crop planting extraction in other area.