Thanks for pointing to the link, which perhaps should be mentioned in the "individual documentation", which is what users check to find help. The actual recipe is using a generic "input_image" as input. I think it would be better an actual example as done in the "individual documentation". Also, despite making reference to the article by Michel, Youssefi and Grizonnet, the actual values of the parameters do not follow the recommended relationship of 50% value for range and spatial radii between step 1 and step 2. Finally, the sentence "The segmentation will group together adjacent pixels whose range distance is below the ranger parameter and (optionally) spatial distance is below the spatialr parameter" is confusing because adjacent pixels are, by definition, at an spatial distance of 1. I think you should use "neighboring" instead of adjacent, or clarify that you use "adjacent" in a generalized way in which adjacency is assumed for pixels at an spatial distance < spatialr.
Agus On Mon, Mar 20, 2017 at 10:07 AM, Guillaume Pasero <[email protected]> wrote: > Hi Agustin, > > The individual documentation of each application is not recommended to > understand the full chain. For large scale segmentation, the corresponding > recipe is : > > https://www.orfeo-toolbox.org/CookBook/recipes/improc.html#large-scale-mean-shift-lsms-segmentation > > However I understand your point. I think we can harmonize example lines. > > Guillaume > > > On 03/17/2017 04:54 PM, Agustin Lobo wrote: > > In the Exact Large-Scale Mean-Shift segmentation section of the cookbook, > otbcli_LSMSSegmentation uses smooth.tif as input > (https://www.orfeo-toolbox.org/CookBook/Applications/app_LSMSSegmentation.html) > > , but in step 1 the output of otbcli_MeanShiftSmoothing is > MeanShift_FilterOutput.tif > (https://www.orfeo-toolbox.org/CookBook/Applications/app_MeanShiftSmoothing.html) > > It would be helpful for learning users keeping a consistent chain, > including > the necessary relationship between ranger and spatialr in the first 2 steps. > > Agus > > > -- > Guillaume PASERO > Responsable technique > Business Unit ESPACE & GeoInformation - Département Payload Data & > Applications > > CS Systèmes d'Information > Parc de la Grande Plaine - 5, Rue Brindejonc des Moulinais - BP 15872 > 31506 Toulouse Cedex 05 - FRANCE > +33 561 17 64 21 - [email protected] > > -- > -- > 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. -- -- 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.
