My ERDAS 2013 does not have the advanced Image Objective Extension for feature extraction.. I am using thus the tool Image Segmentation (Unsupervised -> Image Segmentation) to classify my RGB image ... when I try to use the Segmented Image as a base for classification ( the signature combined of unsupervised and supervised, I also tryed a saparate unsupervised and supervised signature) I constantly obtain a message: Layer count in input image (1) does not match layer count in signatures (3)

should I vectorise the segmentated picture, obtain zonal statistics from the original image based on the segmanted polygons (ARCgis)? I heard many use this method, but how to classify the picture afterwards, since the result will be only in the table?

btw. I know SPRING, MONTEVERDI, ORFEO, SAGA, those tools are not able to work on my huge set of data, and I do not have time to split my pictures in tiny elements...but ERDAS was able to segment and classify this size of data....

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.