I have a WorldView2 image, which I would like to segment and classify in eCognition. The image has been pre-processed to Top of the Atmosphere Reflectance, therefore hasvalues between 0-1.
The segmentation process in eCognition does not show any meaningful results and I think that is likely due to the fact that it does round decimal values. Is there a way to prevent that from happening? I would rather not have to convert to int.