Hello, I'm looking for an explanation about the relation between the typical paramters used in eCognition for the segmentation process (scale, shape, compactness), and those used in the various tools of the OTB. I know each specific method uses different parameters, so lets reduced to the Meanshift segmentation. Could be a proper research paper or report you know, or even the opinion of someone who have done this kind of comparison in the past. I have searched a lot and haven't found any document or forum's answer related to it.
I'm interested in this information because I'm using satellite images for identification of saltmarshes as part of my thesis, and for learning myself about the segmentation (and classification afterwards) and future discussion in research papers and so, I need to compare my results to the others published. The thing is that most of published data use eCognition, and I'm having trouble analyzing/extrapolate what others have done with what I would like to do. I have inferred some of the possible relations between them, but I would like to have a more formal comparison, or at least the opinion of an expert with much more experience in this field than me. Thanks a lot for your help. Felipe -- -- Check the OTB FAQ at http://www.orfeo-toolbox.org/FAQ.html You received this message because you are subscribed to the Google Groups "otb-users" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/otb-users?hl=en --- You received this message because you are subscribed to the Google Groups "otb-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
