Thanks for your reply Jordi! Is there any possibility to define a minimum object size? otbcli_segmentation excludes those objects which fall below the minimum object size. It would be more beneficial to merge small objects with the closest neighboring object with similar attributes. Avoiding to small objects and oversegmentation.
Den måndagen den 27:e januari 2014 kl. 09:26:48 UTC+1 skrev Jordi Inglada: > Johan Viklund > <[email protected]<javascript:>> > wrote: > > > > Hello! > > > > I have a canopy height model which I have extracted from a LiDAR point > cloud. I would like to apply a region growing algorithm where I merge > adjacent pixels that correspond to a certain threshold value (i.e. +-1.5m) > and export the > > output as a .shp-file preferably with the ability to set minimum region > size. How should I go about to achieve this with orfeo toolbox? > > > Hi Johan, > > I think you can use the Segmentation application: > http://www.orfeo-toolbox.org/Applications/Segmentation.html > > You can use the Connected Component algorithm: > > -filter.cc.expr > > and use an expression like "distance < 1.5". > > Cheers, > > Jordi > > > > -- -- 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/groups/opt_out.
