An advanced, AI-powered computer vision application designed for the Indian Armed Forces to detect military vehicles, aircraft, and equipment in real-time. Built with Streamlit and YOLOv8.
- 🎯 Precision Detection: Optimized for military-specific objects using YOLOv8 architectures.
- 🌗 Dual-Theme Interface: Military-themed UI with Dark and Light mode toggles.
- 📄 Professional Reporting: Automatically generates downloadable PDF reports with detection statistics and visualizations.
- 📥 Multiple Export Options: Download annotated images (PNG) and structured surveillance reports (PDF).
- 📊 Real-time Metrics: Track object counts, model confidence, and IOU thresholds on the fly.
- Python 3.8 to 3.11 (Recommended)
- Git
-
Clone the Repository
git clone https://github.com/your-username/military-object-detection.git cd military-object-detection -
Create a Virtual Environment
python -m venv venv # On Windows venv\Scripts\activate # On Mac/Linux source venv/bin/activate
-
Install Dependencies
pip install -r requirements.txt
-
Add Your Model Place your trained
best.ptfile in the root directory. -
Run the Application
streamlit run app.py
├── app.py # Main Streamlit application
├── best.pt # Trained YOLOv8 model weights
├── requirements.txt # Python dependencies
├── .gitignore # Files to exclude from Git
└── README.md # Project documentation
- Computer Vision: Ultralytics YOLOv8
- Web Framework: Streamlit
- Image Processing: OpenCV & PIL
- Report Generation: ReportLab
- Deep Learning: PyTorch
This app is designed to be deployed on Streamlit Community Cloud:
- Push your code to a GitHub repository.
- Connect your GitHub account to Streamlit Cloud.
- Select your repository and the
app.pyfile to deploy.
"The safety, honour and welfare of your country come first, always and every time." — Field Marshal Philip Chetwode
Disclaimer: This is a proof-of-concept application for educational and research purposes.
### Tips for your README:
* **Screenshot**: After you deploy, take a screenshot of your app and add it to the top of the README using ``.
* **Customization**: Change `your-username` and `military-object-detection` in the URLs to match your actual GitHub details.