Supervised Wishart Classification - Quad-pol RADARSAT2


#21

What data are you using?

I just tried again with ALOS QuadPol data:

  1. calibrate
  2. digitize ROIs
  3. Supervised Classification Training
    grafik
  4. Supervised Wishart Classification
    grafik
  5. I now also get the error
    grafik

#22


#23

I use Radarsat2, also get the error, so sad


#24

basically, you can still derive polarimetric decompositions and use them as features for a supervised random forest classification. It’s not based on clusters then but still on the polarimetric features.


#25

Thanks for your patient answer,I will have a try:blush:


#26

if you only have few classes, a k-means clustering might already be sufficient


#27

Another question,If I can decomposition for Sentinel-1A SLC or GRD? Sentinel-1A has only two polarizations.


#28

there are some decompositions which also work for Dual-polarized data but the results are not very good.
There are some discussions on to what extent it makes sense for Sentinel-1 data: