https://github.com/farukalamai/rooftop-solar-counting

Computer Vision to Track Solar Panels on Rooftops
https://github.com/farukalamai/rooftop-solar-counting

computer-vision image-segmentation object-detection yolo11

Last synced: 8 months ago
JSON representation

Computer Vision to Track Solar Panels on Rooftops

• Host: GitHub
• URL: https://github.com/farukalamai/rooftop-solar-counting
• Owner: farukalamai
• License: mit
• Created: 2025-03-19T11:33:48.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-03-19T12:36:22.000Z (8 months ago)
• Last Synced: 2025-03-19T13:34:39.009Z (8 months ago)
• Topics: computer-vision, image-segmentation, object-detection, yolo11
• Language: Jupyter Notebook
• Homepage:
• Size: 87.7 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Counting Solar Adoption: Computer Vision to Track Solar Panels on Rooftops

This computer vision project combines two models: a segmentation model for identifying solar panels on rooftops and a detection model for locating and analyzing rooftops. It also includes counting, which tracks rooftop with and without solar panels to provide insights into adoption rates across regions.

Roboflow’s Auto Labeling feature helps me to streamline dataset annotation. I also used Roboflow’s open-source tool, Supervision, to process drone footage, benefiting from its powerful annotators for smooth and efficient video processing. And YOLO11 (from Ultralytics) for training object detection and segmentation model. 

**Rooftops Datset:** https://app.roboflow.com/facialai-nfkit/rooftop-hixra/1

**Solar Panel Dataset:** https://app.roboflow.com/facialai-nfkit/solar-hapbf/1