In this article, we will go through the process of commercial rooftops classification using Deep Learning methods. And accelerate the installation of solar energy in North America, as a part of Omdena’s challenge with EnergyTech startup.

A walkthrough in understanding the use of labeling tools like CVAT in labeling satellite imagery, the difference between semantic and instance segmentations with rooftops images pixels, and training different pre-trained deep learning models to get the best roof classification results.


Therefore, significant work remains to be done to accelerate the deployment of solar energy in the US by identifying potential locations and rooftops classification.

Problem Statement

 

Data preparation and images labeling

 

Roof classification - Source: Omdena

Demonstration of labeling done on a rooftop in CVAT — source: Omdena

 

Roof classification - Source: Omdena

GIF showing CVAT export formats — source: Omdena

  • Flat: Rooftops with a single flat surface with/without clutters
  • Complex Rooftop: Rooftops with multiple surfaces at different heights
  • Existing Solar: Rooftops with solar panels
  • Heavy Industrial: Rooftops with pipes, and cluttered with machinery
  • Slope: Rooftops with an inclined surface
Image labeling for roof classification - Omdena

Examples of images and their label — Source: Omdena

 

Rooftop Segmentation

We needed to try different segmentation methods to get the best results.

 

Semantic Segmentation

 

Example of mask used for labeling — source: Omdena

Example of mask used for labeling — source: Omdena

U-Net binary segmentation of rooftops — source: Omdena

U-Net binary segmentation of rooftops — source: Omdena

 
 

Multi-classes semantic segmentation results with U-Net — source: Omdena

Multi-classes semantic segmentation results with U-Net — source: Omdena

 
 

Deep-Lab predictions — source: Omdena

Deep-Lab predictions — source: Omdena

 
 

 

Instance Segmentation

Labeled rooftops images exported into COCO format — source: Omdena

Labeled rooftops images exported into COCO format — source: Omdena

 

 

‘AP-flat’: 34.46745607306496
‘AP-slope’: 9.342863008612126
‘AP-existing_solar’: 1.7519702923446772
‘AP-complex_rooftop’: 14.343733930311137
‘AP-heavy_industrial’: 5.055339100777756

Mask R-CNN results — source: Omdena

Mask R-CNN results — source: Omdena

 
 

Examples of the wrong classification with Mask R-CNN — source: Omdena

Examples of the wrong classification with Mask R-CNN — source: Omdena

 
 

Predictions Mask R-CNN — source: Omdena

Predictions Mask R-CNN — source: Omdena

 
 
 

Mask R-CNN improved results with learning rate = 0.001 and 4000 epochs — source: Omdena

Mask R-CNN improved results with learning rate = 0.001 and 4000 epochs — source: Omdena

 

 

Box Localization Loss — 0.70
Confidence Loss — 1.6
Mask Loss — 1.1
Semantic Segmentation Loss — 0.40

Yolact’s results for roof classification — source: Omdena

Yolact’s results for roof classification — source: Omdena

 

 

Final Deliverable

 

Visual of the rooftops classification Streamlit application in the class prediction section of the application — source: Omdena

Visual of the roof classification Streamlit application in the class prediction section of the application — source: Omdena

 

Conclusion

More approaches accomplished by Omdena in the Energy sector – “Machine Learning For Rooftop Detection and Solar Panel Installment” and “AI for Solar Energy Adoption in Sub-Saharan Africa

Develop Your Career and Make a Real-World Impact

Innovation

The world´s only place for truly collaborative AI projects to apply your skills on real-world data with changemakers from around the world.

Apply & grow your skills in our real-world projects

Upcoming AI Projects

AI Teams

Make an impact in our upcoming projects in Natural Language Processing, Computer Vision, Machine Learning, Remote Sensing, and more.

Check out our projects!

Stay in touch via our newsletter.

Be notified (a few times a month) about top-notch articles, new real-world projects, and events with our community of changemakers.

Sign up here