Mapflow Web UI¶
Go to Mapflow and register or login using your Google account. Mapflow processes imagery and extracts vector objects from it. So as a user, you start processings, or as we call it, flows.
How to run your mapping flow¶
Mapflow is designed to be intuitive. Here is our step-by-step user guide:
To specify your area of interest (AOI), you can either upload your own GeoJSON file, or draw the area directly on the map (“Draw rectangle”).
Be aware that for now, only a single area can be drawn or uploaded per flow. If your GeoJSON file has multiple areas within its FeatureCollection, only the first one will be used. If you want to process multiple AOIs, you can split them into separate GeoJSON files and start a flow for each one separately. Batch processing may become available in the future releases. Other spatial data formats may also become available for upload in the future, although we recommend using GeoJSON since it is a de-facto standard in web mapping. It is natively supported by web mapping frameworks (e.g. Leaflet or Mapbox) and GIS like QGIS or the ArcGIS Suite.
As to the source data, currently we only support RGB imagery. By default, Mapflow uses Mapbox Satellite imagery. Currently, this is the only available source when using the web app. If you would like to upload your own GeoTIFF or choose another satellite imagery mosaic as a service, you can use Processing API.
Select one of the AI models (See Model description).
In this step, you can select additional processing options. Different AI models have their own options.
AI model “Buildings”:
Classification - we currently recognize the following building types: apartment buildings, single-household dwellings, industrial, commercial, other non-reidential (see Urban Mapping classes).
Merge with OSM - compare the results with the buildings in OpenStreetMap and, if a sufficient overlap has been found, use the ones from the OSM instead.
Simplification - simplification and polygonization of building contours.
Building heights - for each building, we estimate its height using its wall’s and shadow’s length. If this option is selected, all roof contours will be shifted in accordance with their height, i.e. converted to footprints.
Building heights option requires a minumum area of 50 sq.km.
AI model “Forest”:
Tree heights - classify vegetation by height: 0-4 m for shrub (“low vegetation”), 4-10 m for regular forest (“medium forest”), 10+ m for area with tall trees (“high forest”). Clasification is dones per vegetated area, and not per single tree (see Forest Mapping classes).
Run the flow
Once you have selected the model and the processing parameters, you will see the total cost of your flow counted in Mapflow credits (our local currency units). Upon registration, you receive 500 credits for free for testing the platform (See the tariff plan).
Working with results¶
The flow’s results are saved in the “Job history” panel. When this panel is opened, the status is displayed, and the previously selected processing parameters are highlighted in the main window.
Once the flow has finished, you can view the results on an interactive map or download it as vector geodata (GeoJSON).
Click “use as template” on an existing flow to use its parameters as a starting point for a new flow (on restart with the same parameters, a new processing is started).
Options for viewing the processing results are:
Download as GeoJSON.
“Open with geojson.io” - view the results in the browser using geojson.io.
geosjon.io also allows you to save the results in a different format (CSV, KML, TopoJSON, WKT, Shapefile). Just click “Save” and select the format of your preference in the menu bar.
“View on the map” - use our custom viewer, which displays the results on top of the source satellite images.
“Open with kepler.gl” - view the results using an open-source web tool made by Uber. It is a simple but powerful tool for data scientists to explore and analyse geospatial data.
You can find detailed information about kepler.gl in the user manual.