Welcome to the Solar Vision project developed under the National Remote Sensing Centre (NRSC) of ISRO. This repository hosts the code and resources for a deep learning-based solution to detect solar panels from spatial images. The project aims to enhance the efficiency of solar energy monitoring and analysis using advanced computer vision techniques.
The Solar Vision project utilizes state-of-the-art object detection models to identify and analyze solar panels in high-resolution satellite images. This technology can significantly aid in solar energy assessment and planning, providing valuable insights into solar infrastructure across various regions.
For a comprehensive overview of the project, including its objectives, methodology, and expected outcomes, please visit our project poster website:
The project offers two inference platforms where users can upload images to analyze solar panel coverage:
-
High-Resolution Inference Site: This site processes high-resolution images to detect solar panels. Access it here: High-Res Inference
-
Low-Resolution Inference Site: This site is optimized for low-resolution images, providing quick results with acceptable accuracy. Access it here: Low-Res Inference
- Real-time Solar Panel Detection: Users can upload images, and the model will identify solar panels in real-time.
- User-Friendly Interface: The inference sites are designed with a simple and intuitive interface to facilitate easy interaction.
- Multiple Resolution Support: Choose between high-resolution and low-resolution image processing based on your needs.
- Visit the inference websites, upload your images, and receive results in a matter of seconds.
- The outputs include detection results visualized on the uploaded image.
We welcome contributions to enhance the project further. Feel free to open issues or submit pull requests for new features or bug fixes.
- National Remote Sensing Centre (NRSC) - ISRO for supporting this initiative.
- Contributors and collaborators who have helped in the development of this project.
For more information and updates, please follow our GitHub Repository.
- If you have a contributing guideline or code of conduct, you can include those as well.
