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....
أكثر...
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....
أكثر...