Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/d-d-roshan/solar-panel-detection

Last synced: about 1 month ago
JSON representation

Host: GitHub
URL: https://github.com/d-d-roshan/solar-panel-detection
Owner: D-D-Roshan
Created: 2024-03-28T10:10:10.000Z (9 months ago)
Default Branch: main
Last Pushed: 2024-08-15T13:19:51.000Z (4 months ago)
Last Synced: 2024-08-15T14:57:54.768Z (4 months ago)
Language: Python
Size: 7.33 MB
Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

# Solar Panel Detection from Aerial Images

This project aims to detect solar panels in aerial satellite images using machine learning techniques. By segmenting images into smaller data segments and employing a Convolutional Neural Network (CNN), the model identifies solar panels and calculates the number of solar panel houses out of the total number of houses in a city.

## Features

- **Image Segmentation:** Divides aerial images into smaller segments for detailed analysis.
- **Solar Panel Detection:** Identifies solar panels using a CNN model.
- **Count Calculation:** Returns the number of solar panel houses relative to the total number of houses.
- **Python-Based:** Implemented using Python with popular machine learning and computer vision libraries.

## Technologies Used

- **Python:** Programming language for implementing the machine learning model.
- **OpenCV:** For image processing and manipulation.
- **Keras:** For building and training the Convolutional Neural Network (CNN).
- **NumPy/Pandas:** For data handling and manipulation.

## Installation

1. Clone the repository:
```bash
git clone https://github.com/D-D-Roshan/solar-panel-detection
```

2. Navigate to the project directory:
```bash
cd solar-panel-detection
```

3. Install dependencies:
```bash
pip install -r requirements.txt
```

4. Ensure you have the required datasets. The dataset should be in the `data/` directory. You may need to download it separately if not included.

## Screenshots

1. Images with the solar panel
![images with solar panel](https://github.com/D-D-Roshan/solar-panel-detection/blob/main/Figure_1.png)

2. Images with no solar panel
![images no with solar panel](https://github.com/D-D-Roshan/solar-panel-detection/blob/main/output1.png)

*Example of solar panel detection results.*

## Contact