Hi, I would like to repost my question about processing nodata values in the different otb functions, unsupervised classifications in particular. How to assign specific values to nodata pixels, and exclude them from treatments? is the use of masks the right solution? Thanks for your help
Regards, Julien Le mardi 10 avril 2018 11:40:03 UTC+2, Julien a écrit : > > Hi, > I tried to perfom an unsupervised classification using Kmeans algorithm. > My first question is : is this algorithm uses all the bands in case of > using it on a multispectral image? or does it use only the first band of > the image? > I tried to use it on subset of my image extracted with gdalwarp. I decided > to attribute nodata value to -9999 during the process. > When I perform the kmeans classification, i can see that statistics > parameters of my image used by the algorithm include no data value (so mean > and stddev generated are false), and i can't avoid that. > I tried to use a mask (using -vm pathotoimagemask.tif), but it doesn't > change anything. > Coud you help me? > > Thanks > > Regards, > Julien > -- -- 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.
