Hi Dmitriy, Jus a guess, but if you are using S2 reflectance images where the pixel values are reflectance * 10000, maybe you have to tune the -filter.meanshift.ranger parameter so that it is in the appropriate range.
Jordi On Fri 08-Dec-2017 at 08:17:58 +0100, Dmitriy Hramov <dmitriy.hra...@eosda.com> wrote: > Hi all, > > I tried to perform a Mean Shift segmentation the subset of the Sentinel-2 > image (S2A_tile_20170801_36UVA_0, Band 4) using otbcli_Segmentation: > > otbcli_Segmentation -in yasubset.tif -mode raster -mode.raster.out > SegmentationRaster.tif uint32 -filter meanshift > > and got the file that consists of only 1's. > > For verification I took QB_Toulouse_Ortho_PAN.tif and the result was regular. > > I also tried a step-by-step LSMS to my image: > > otbcli_MeanShiftSmoothing -in yasubset.tif -fout filtered_range.tif -foutpos > filtered_spatial.tif -ranger 30 -spatialr 5 -maxiter 10 -modesearch 0 > otbcli_LSMSSegmentation -in filtered_range.tif -inpos filtered_spatial.tif > -out SegmentationRaster.tif uint32 -ranger 30 -spatialr 5 -minsize 0 > -tilesizex 256 -tilesizey 25 > > and again got the file of 1's, whereas with QB_Toulouse_Ortho_PAN.tif > everything work fine. > > Any suggestions about this? > > -- -- -- 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 otb-users@googlegroups.com To unsubscribe from this group, send email to otb-users+unsubscr...@googlegroups.com 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 otb-users+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
