I have performed a RF classification in my image and I found some miss classification there, I want to recode those miss classified pixel using Erdas but I could not, Because while exporting it in geotiff format class information is being lost.
can you specify how the class information is different after exporting to GeoTiff?
You can save the Random Forest Classification in BEAM DIMAP format and then import the img file (ERDAS expects you to select the LabeledClasses.hdr file)
Please check the “Notes on exporting results” chapter of this tutorial: Landcover classification with Sentinel-1 GRD
Is there a way to do the opposite? Making the img or tiff products from Erdas Imagine be imported into a readable format in snap (while keeping their geocoordinate data intact)?
i appreciate the response. I have also tried the same but unfortunetely didn’t load and this error appeared
java.lang.NullPointerException: Failed opening a dataset from the file ‘I:\RadarData\Ataqa\P58_F92\project_93\terrain_corrected_coherence\Stable_PS_pixels\persistent_coherence_test.img’ to load the product.
at org.esa.s2tbx.dataio.gdal.reader.GDALProductReader.openGDALDataset(GDALProductReader.java:87)
at org.esa.s2tbx.dataio.gdal.reader.GDALProductReader.readProduct(GDALProductReader.java:284)
at org.esa.s2tbx.dataio.gdal.reader.GDALProductReader.readProductNodesImpl(GDALProductReader.java:253)
at org.esa.snap.core.dataio.AbstractProductReader.readProductNodes(AbstractProductReader.java:178)
at org.esa.snap.core.dataio.ProductIO.readProduct(ProductIO.java:182)
at org.esa.snap.rcp.actions.file.ReadProductOperation.run(ReadProductOperation.java:61)
at org.openide.util.RequestProcessor$Task.run(RequestProcessor.java:1443)
at org.netbeans.modules.openide.util.GlobalLookup.execute(GlobalLookup.java:68)
at org.openide.util.lookup.Lookups.executeWith(Lookups.java:303)
[catch] at org.openide.util.RequestProcessor$Processor.run(RequestProcessor.java:2058)
And I tried importing a .tif file instead of an .img file from Erdas imagine and it did load into SNAP but the location has been altered from its original
like this