{"id":25376506,"url":"https://github.com/akhundmuzzammil/superresolutionsatellite","last_synced_at":"2026-04-14T03:32:34.306Z","repository":{"id":277414203,"uuid":"932333579","full_name":"akhundmuzzammil/SuperResolutionSatellite","owner":"akhundmuzzammil","description":"SuperResolutionSatellite is a deep learning project that enhances the resolution of satellite imagery using a Super Resolution Convolutional Neural Network (SRCNN).","archived":false,"fork":false,"pushed_at":"2025-02-13T19:38:40.000Z","size":20125,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-13T20:31:06.763Z","etag":null,"topics":["computer-vision","deep-learning","image-enhancement","keras","python","satellite-imagery","srcnn","streamlit","super-resolution","tensorflow"],"latest_commit_sha":null,"homepage":"https://superresolutionsatellite.streamlit.app","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/akhundmuzzammil.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-13T18:40:02.000Z","updated_at":"2025-02-13T19:38:43.000Z","dependencies_parsed_at":"2025-02-13T20:41:57.301Z","dependency_job_id":null,"html_url":"https://github.com/akhundmuzzammil/SuperResolutionSatellite","commit_stats":null,"previous_names":["akhundmuzzammil/superresolutionsatellite"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akhundmuzzammil%2FSuperResolutionSatellite","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akhundmuzzammil%2FSuperResolutionSatellite/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akhundmuzzammil%2FSuperResolutionSatellite/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akhundmuzzammil%2FSuperResolutionSatellite/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/akhundmuzzammil","download_url":"https://codeload.github.com/akhundmuzzammil/SuperResolutionSatellite/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248017998,"owners_count":21034042,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","deep-learning","image-enhancement","keras","python","satellite-imagery","srcnn","streamlit","super-resolution","tensorflow"],"created_at":"2025-02-15T04:28:06.437Z","updated_at":"2026-04-14T03:32:34.261Z","avatar_url":"https://github.com/akhundmuzzammil.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SuperResolutionSatellite\n\nSuperResolutionSatellite is a deep learning project that enhances the resolution of satellite imagery using a Super Resolution Convolutional Neural Network (SRCNN). It provides both a Streamlit web application for real-time image enhancement and a command-line interface for training, evaluating, and running inference.\n\n## Features\n\n- **Real-Time Image Enhancement:** Use the Streamlit app ([app.py](app.py)) to upload and enhance satellite images.\n- **Model Training \u0026 Evaluation:** Train, test, and run model inference using the CLI tool ([srcnn.py](srcnn.py)).\n- **Data Preprocessing:** Automatically generate training and testing samples from large images ([preprocess.py](preprocess.py)).\n- **Utility Functions:** Data loading and directory management functionalities in ([util.py](util.py)).\n\n## Requirements\n\n- Python 3.7+\n- TensorFlow 2.x / Keras\n- Streamlit\n- Other dependencies listed in [requirements.txt](requirements.txt)\n\n## Installation\n\n1. **Clone the Repository:**\n   ```sh\n   git clone \u003crepository-url\u003e\n   cd SuperResolutionSatellite\n   ```\n\n2. **Install Dependencies:**\n   ```sh\n   pip install -r requirements.txt\n   ```\n\n3. **Download Model Weights:**\n   Place the pre-trained model weights (e.g., weights.h5 or weights2.h5) into the models directory.\n\n## Usage\n\n### Streamlit App\n\nLaunch the app to enhance your satellite images:\n\n```sh\nstreamlit run app.py\n```\n\n- **How It Works:**  \n  Upload an image, then click on \"🚀 Enhance Image\". The app displays the original and enhanced images side-by-side with a download option for the result.\n\n### Command Line Interface\n\nUse the CLI tool in srcnn.py for these actions:\n\n- **Train the Model:**\n  ```sh\n  python srcnn.py --action train --data_path data --model_path models/weights2.h5\n  ```\n\n- **Test the Model:**\n  ```sh\n  python srcnn.py --action test --data_path data --model_path models/weights2.h5\n  ```\n\n- **Run Inference:**\n  ```sh\n  python srcnn.py --action run --data_path data --model_path models/weights2.h5 --output_path results\n  ```\n\n## Data Preprocessing\n\nThe preprocessing routines in preprocess.py split large images, generate dataset samples, and create corresponding downsampled versions for training.  \n- Place your high-resolution images in the `images/` directory.\n- The scripts generate subdirectories for raw, training, and testing data.\n\n## App Screenshots\n\nView screenshots of the application:\n\n- ![Screenshot 1](screenshots/screenshot1.png)\n- ![Screenshot 2](screenshots/screenshot2.png)\n- ![Screenshot 3](screenshots/screenshot3.png)\n\n*Ensure your `/screenshots` folder contains these images.*\n\n## File Structure\n\n```plaintext\napp.py\ndata/\n  └── images/\nmodels/\n  ├── weights.h5\n  └── weights2.h5\npreprocess.py\nREADME.md\nsrcnn.py\nutil.py\n```\n\n## Troubleshooting\n\n- Ensure all dependencies are installed correctly using:\n  ```sh\n  pip install -r requirements.txt\n  ```\n- Verify your Python version is 3.7 or above.\n- Check that the model weights are placed in the correct directory.\n\n## Contributing\n\nContributions are welcome! Please follow these steps:\n- Fork the repository.\n- Create a feature branch: `git checkout -b feature/YourFeature`.\n- Commit your changes and push to your branch.\n- Open a pull request with a clear description of your changes.\n\n## License\n\nThis project is licensed under the [MIT License](https://opensource.org/licenses/MIT).\n\n## Acknowledgments\n\n- **Streamlit:** For the intuitive web interface.\n- **TensorFlow/Keras:** For the underlying deep learning framework.\n- **SRCNN Paper:** For inspiring the super resolution approach ([Link to paper](https://arxiv.org/pdf/1501.00092.pdf)).\n- **WarrenGreen:** For contributions to the training code ([GitHub](https://github.com/WarrenGreen/srcnn)).\n\n## Future Work\n\n- Implement automated model optimization.\n- Add more robust error handling in the CLI.\n- Expand the web app features for batch processing.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakhundmuzzammil%2Fsuperresolutionsatellite","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fakhundmuzzammil%2Fsuperresolutionsatellite","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakhundmuzzammil%2Fsuperresolutionsatellite/lists"}