Krzysztof Dyba

So I tested my workflow on Landsat scene. Segmentation took ~1 hour on raster with 7 bands (8261 x 8201 pixels; non scaled) and 2000 clusters (kmeans algorithm). Below is...

Some my observations from the comparison: 1. It seems `supercells` is ~10x faster than what I proposed. This is mainly due to the fact that the [prediction function](https://github.com/kadyb/image-segmentation/blob/c4ca98e11fed921bc8c72a22ac0cae4b90f2ceeb/landsat.R#L25-L35) is very...

Thanks! One more thing, in the distant future it would be nice considering more advanced approaches, e.g. region growing (in [GRASS](https://grass.osgeo.org/grass82/manuals/i.segment.html)) or OBIA.

This is a good point. Integer has the advantage of taking up half the space than double. For example, `{sf}` just returns an integer, but like you said it won't...

Shouldn't you use a planar CRS (eg 2263)? It looks like the difference is even greater then. ``` result = bench::mark( check = FALSE, iterations = 10, time_unit = "s",...

```r req_df = DEM_request(counties_geom) #> Warning message: #> In DEM_request(counties_geom) : maximum number of records, reduce the area ``` Hi! This is not an error, but a warning and is...

> > > Hi ! > > Do you plan to add the possibility of downloading LiDAR data ? > > By the way, you have done nice work with...

@GreKro I added possibility of downloading all DEM products including point clouds. Here is example: ```r remotes::install_github("kadyb/rgugik") library("sf") library("lidR") library("rgugik") # load your polygon with area of interest polygon_path =...

We have currently implemented all shared datasets (except _Ewidencja Gruntów i Budynków_, but there is no proper sharing infrastructure, maybe this will change in the future). Additionally, we could implement...

_Ewidencja Gruntów i Budynków_ is provided as a WFS service (not all counties are available). How can we deal with it in R: - [Using WFS service in R](https://inbo.github.io/tutorials/tutorials/spatial_wfs_services/) -...