[Qgis-user] Set new pixel radiometric values ​based on neighborhood?

[celati Laurent]

Thanks so much for your reply.  r.neighbours :
grass.osgeo.org/grass-stable/manuals/r.neighbors.html is probably more
appropriate. Even if i notice one limit : the tool handles only raster with
one band (input). No multi bands.

Le mer. 3 déc. 2025 à 13:22, Richard McDonnell <richard.mcdonnell at opw.ie> a
écrit :

> Hi,
>
> The Fill NoData tool would seem to be the tool you should look at. But you
> would have to use the mask to set all pixels in the shadowed regions to
> NoData, then run the Fill NoData tool
>
> (Raster è Analysis è Fill NoData)
>
>
>
> Kind Regards,
>
>
>
> Richard
>
>
>
> ——
> Richard McDonnell MSc GIS
> *Flood Risk Management - Data Management*
>
> ——
> Oifig na nOibreacha Poiblí
> Office of Public Works
>
> Sráid Jonathan Swift, Baile Átha Troim, Co na Mí, C15 NX36
> Jonathan Swift Street, Trim, Co Meath, C15 NX36
> ——
> M +353 87 688 5964 T +353 46 942 2409
> https://gov.ie/opw
>
> ——
> To send me files larger than 30MB, please use the link below
> https://filetransfer.opw.ie/filedrop/richard.mcdonnell@opw.ie
>
> Email Disclaimer:
> https://www.gov.ie/en/organisation-information/439daf-email-disclaimer/
>
> *From:* QGIS-User <qgis-user-bounces at lists.osgeo.org> *On Behalf Of *celati
> Laurent via QGIS-User
> *Sent:* 03 December 2025 10:11
> *To:* qgis-user <qgis-user at lists.osgeo.org>
> *Subject:* [Qgis-user] Set new pixel radiometric values ​based on
> neighborhood?
>
>
>
>
>
> Dear all,
>
>
>
> I work with Qgis (especially with processing tools allowing to use qgis,
> orfeotoolbox, grass, saga tools). I'm performing segmentations on infrared
> aerial images (3 bands : NIR, R, G).
>
>
> One of the problems comes from shadow (especially from trees) which
> affects the segmentation results. Based on an analysis of the spectral
> signatures of the shadow pixels, I managed to generate a mask of these
> pixels.I paste below a screenshot showing the aerial data + the aerial data
> with this cloud mask.
>
> The idea (which might be bad) would be to generate a new aerial data by
> modifying the radiometric values of the three NIR, R, and V bands of the
> aerial data only for these shadow pixels. I thought one approach would be
> to define a new radiometric value for these pixels based on the values of
> neighboring pixels not affected by the shadow mask? In other words, the new
> radiometric values of the shadow pixels in aerial data would correspond to
> neighboring radiometric values (tree vegetation, agricultural plot, etc.).
> This is intended to mitigate the impact of shadow pixels on subsequent
> segmentation a posteriori.
>
> Is there a QGIS tool or another (OTB, GRASS, Saga) that would allow
> defining new radiometric values only for certain pixels of a multiband
> raster, based on neighboring radiometric values? (A kind of nearest
> neighborhood averaging, using a sliding window? or other).
>
>
>
> Thanks so much
>
>
> [image: image.png]
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osgeo.org/pipermail/qgis-user/attachments/20251203/376ac48f/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 392827 bytes
Desc: not available
URL: <http://lists.osgeo.org/pipermail/qgis-user/attachments/20251203/376ac48f/attachment-0001.png>