2

I recently produced map of LULC but there is the difficulty of distinguishing between the types of crops. Is there a method to distinguish between the types of cultivated crops such as wheat, barley, maize etc.?

  • 2
    The spectral response should be different in theory. But it also depends on the time when the image was taken during the life of the crop, as well as radiometric resolution of the satellite. That's why in practice it might not be that easy. – Devdatta Tengshe Feb 11 '14 at 12:30
  • 4
    What is your study area ? What kind of data do you use (high or low spatial, temporal and radiometric resolution ? MODIS, MERIS, Aster, Landsat, SPOT, Quickbird...) How many cloud free images do you have ? Do you have field observation to train your classification algorithm i.e. do you use unsupervised or supervised classification ? Basically, a crop classification can only be effective using several images taken along the season thanks to their temporal signatures. The literature is packed with examples in this area. – DJack Feb 11 '14 at 13:20
  • 1
    Going along with what Devdatta Tengshe stated in theory there should be a difference in spectral signatures depending on a number of factors. I have done a similar analysis on a small scale using ENVI software and supervised classification methods like Neural Net and Maximum Likelihood also a fair amount of processing before classification to identify spectral signatures and to mask those spectral ranges which I didn't want to classify and post classification to smooth and clean up the results. Depending on how precise/accurate you want the classification to be this can be quite complicated. – landocalrissian Feb 11 '14 at 13:31

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.