Adom-Amponsah/Ghana-Agricultural-Field-Boundary-Detection

Ghana Agricultural Field Boundary Detection # 🌾 Ghana Agricultural Field Boundary Detection This project uses AI-powered methods to detect agricultural field boundaries in Ghana from **.tif geospatial data** (such as maize production raster files). It provides both a **model pipeline** and a **Streamlit-based interactive dashboard** for visualization and analysis. --- ## 📌 Features - Upload a `.tif` geospatial file (e.g., Ghana maize production data for 2024). - Process the file using multiple delineation methods: - Watershed Segmentation - K-means Clustering - Threshold-based Segmentation - Contour Detection - Visualize: - Original production raster - Detected field boundaries - Overlay maps - Export results: - Boundary maps (PNG) - Field statistics (CSV) - Summary report (TXT) --- ## ⚙️ Installation & Setup Clone the repository: ```bash git clone github.com cd Ghana-Agricultural-Field-Boundary-Detection ``` Create and activate a virtual environment (recommended): ```bash python -m venv venv # Activate the environment # On Mac/Linux: source venv/bin/activate # On Windows: venv\Scripts\activate ``` Install dependencies: ```bash pip install -r requirements.txt ``` If you don’t have `requirements.txt`, install manually: ```bash pip install streamlit rasterio matplotlib scikit-image scipy pandas pillow plotly scikit-learn opencv-python ``` --- ## ▶️ Running the Application Start the Streamlit dashboard with: ```bash streamlit run ghana_field_demo.py ``` This will launch a local server. Open the link shown in your terminal (e.g., `localhost`) in your browser. --- ## 📂 Project Structure ``` . ├── ghana_field_demo.py # Main Streamlit application ├── ghana_field_boundaries.tif # Example output (if available) ├── requirements.txt # Dependencies └── README.md # Project documentation ``` --- ## 📊 Example Workflow 1. Upload your `.tif` maize production raster (e.g., Ghana_Predicted_Maize_P …