Course Hive
Search

Welcome

Sign in or create your account

Continue with Google
or
GeoAI QGIS Plugin: Step-by-Step Setup for AI Detection & Image Segmentation
Play lesson

GeoAI Tutorials - GeoAI QGIS Plugin: Step-by-Step Setup for AI Detection & Image Segmentation

4.0 (2)
23 learners

What you'll learn

This course includes

  • 20 hours of video
  • Certificate of completion
  • Access on mobile and TV

Summary

Keywords

Full Transcript

🚀 GeoAI is now inside QGIS — no coding required. In this tutorial, I show you how to install and set up the GeoAI QGIS plugin so you can run Moondream vision-language models, object detection, image segmentation (SAM 3), and even train your own geospatial segmentation model end-to-end. Website: https://opengeoai.org/qgis_plugin GitHub: https://github.com/opengeos/geoai Short demo: https://youtu.be/Esr_e6_P1is Full video tutorial: https://youtu.be/8-OhlqeoyiY #QGIS #GeoAI #SAM3 #Geospatial #GIS #DeepLearning #ComputerVision #OpenSource #Python Timestamps: ### ⏱️ Installation **00:00** Introduction: GeoAI Plugin for QGIS Overview **00:29** What the GeoAI Plugin Can Do (VLMs, Detection, Segmentation, Training) **01:44** GeoAI Plugin Interface Tour in QGIS **02:14** Why Conda Is Required for GeoAI + QGIS **02:59** Creating a New Conda Environment **04:41** Installing GDAL, Rasterio & Core Dependencies **06:38** Installing GeoAI (GPU / PyTorch with CUDA) **08:28** Installing QGIS from conda-forge **09:49** Installing SAMGeo / SAM 3 Dependencies via pip **10:30** Verifying Install (Rasterio, GeoAI, SAMGeo Imports) **10:55** Launching QGIS from Conda **11:28** Installing the GeoAI Plugin from GitHub **13:41** Enabling the GeoAI Plugin in QGIS ### 🌍 Vision-Language Models (MoonDream) **14:24** Loading MoonDream Vision-Language Model **15:29** Image Captioning for Geospatial Imagery **16:40** Visual Question Answering (Ask Questions About Imagery) **17:19** Text-Prompt Object Detection (Bounding Boxes) **18:59** Point-Based Object Detection **19:49** GPU Memory Management (Clearing GPU) ### 🧠 Training Your Own Segmentation Model **20:38** Preparing Training & Testing Datasets **24:28** Exporting Image Chips & Labels **26:21** Configuring Model Architecture & Training Parameters **28:14** Training the Segmentation Model on GPU **29:30** Reviewing Model Outputs & Training Metrics ### 🛰️ Model Inference & Post-processing **30:51** Running Inference on New Imagery **32:23** Viewing Segmentation Masks in QGIS **33:32** Vectorizing Masks & Removing Small Artifacts **34:25** Rectangularizing Building Footprints ### ✂️ SAM 3 Segmentation in QGIS **35:51** Loading SAM 3 Model (Hugging Face Authentication) **37:17** Text-Prompt Segmentation with SAM 3 **38:29** Interactive Point-Based Segmentation **39:21** Box-Prompt Segmentation (Find Similar Objects) **40:32** Interactive Brush Segmentation **42:03** Using Existing Point Layers for Segmentation ### 🔚 Wrap-up **42:31** Releasing GPU Resources **42:49** Future GeoAI Features & Roadmap **43:07** Final Thoughts & Community Feedback --------------------------------------------------------- 📌 More Resources: 📺 GeoAI Playlist: https://www.youtube.com/playlist?list=PLAxJ4-o7ZoPcvENqwaPa_QwbbkZ5sctZE 📚 Get My Books: 📘 Introduction to GIS Programming: A Practical Python Guide to Open Source Geospatial Tools 👉 Amazon: https://amazon.com/dp/B0FFW34LL3 👉 Leanpub: https://leanpub.com/gispro 📘 Spatial Data Management with DuckDB: From SQL Basics to Advanced Geospatial Analytics 👉 Amazon: https://amazon.com/dp/B0G2JFMFFC 👉 Leanpub: https://leanpub.com/duckdb 👋 Let’s Connect: YouTube: https://youtube.com/@giswqs LinkedIn: https://www.linkedin.com/in/giswqs Twitter: https://twitter.com/giswqs Facebook: https://www.facebook.com/groups/opengeos

Course Hive

Continue this lesson in the app

Install CourseHive on Android or iOS to keep learning while you move.

Related Courses

FAQs

Course Hive
Download CourseHive
Keep learning anywhere