Tag: ai segmentation

Semantic vs Instance Segmentation on Aerial Imagery

Semantic segmentation labels every pixel with a class: building or not. Instance segmentation draws every building as its own object.
Learn More

How to Add a Basemap in QGIS: XYZ, WMS and Plugins

Browser panel, XYZ Tiles, double-click OpenStreetMap. Then Google, Esri and Bing by URL, national imagery by WMS, and which basemap a detection model can read.
Learn More

Detect Solar Panels in QGIS: 5 Methods

Check OpenStreetMap first. Then four ways to map rooftop PV from aerial imagery in QGIS, with the menu paths and where each one fails.
Learn More

Detect Swimming Pools in QGIS: 5 Methods

Start with QuickOSM on leisure=swimming_pool. Where the map is thin, threshold the blue, run a water index, or use a segmentation model. Five methods compared.
Learn More

Extract Roads in QGIS: 6 Methods and One Trap

Start with QuickOSM. Where OSM is thin, five more ways to get roads out of imagery, and the line-or-surface choice that decides all of them.
Learn More

Map Tree Canopy in QGIS: 6 Methods, Free and Paid

For multispectral imagery, threshold NDVI in the raster calculator, then polygonize. Six methods, what each one needs, and what a canopy layer costs.
Learn More

Detect Building Footprints in QGIS: 3 Methods

Draw a zone, name the object, run it: you get a polygon layer in minutes. Open data, hand-digitizing and AI detection compared, with the filtering step.
Learn More

Segment Anything (SAM) in QGIS: 7 Plugins Compared

SAM outlines an object from a click or a word. Seven QGIS plugins run it: what each costs, which needs an NVIDIA card, and how to install one.
Learn More

AI Segmentation for QGIS: The Complete Guide

Draw a zone, name the object, get every polygon as a clean vector layer. The full run in QGIS, the three-step review in any order, and Semi-Auto mode.
Learn More