VISTA-S: Visual Inference System for Target Assessment

DualityAI Space Station Model

Welcome to VISTA-S — a cutting-edge, high-precision AI system for object detection and visual inference.
Inspired by the mysteries of space, VISTA-S delivers powerful computer vision capabilities with ease and elegance. 🌌

---

✨ Features

• State-of-the-Art Detection: Built on YOLOv8 for high-precision object detection.
• Optimized Performance: Fast, efficient inference for real-time applications.
• Interactive Demo: Visualize and interact with predictions through an easy-to-use web app.
• Seamless Data Integration: Streamlined data preparation and handling for a smooth workflow.

---

📸 VISTA-S in Action

---

⚡ Quickstart

Get up and running in minutes!

1. Create Environment

conda env create -f environment.yaml

2. Activate Environment

conda activate VISTA

---

📦 Data Preparation

• Download the Falcon Dataset:
  Download here

• Unzip & Place:
  Extract the dataset and copy its contents to:

  data/raw/
  

Note: The dataset is NOT included in this repository due to its size. Please download it manually.

---

🏋️‍♂️ Training

Train the model on your machine:

python src/train.py

---

🔍 Inference

Detect objects in a sample image:

python src/detect.py data/raw/test/images/sample.jpg

---

🖥️ Demo Application

Experience VISTA-S through the interactive web app:

1. Navigate to the app directory:

   cd app

2. Install requirements:

   pip install -r requirements.txt

3. Start the backend server:

   python backend.py

---

📊 Performance

VISTA-S achieves exceptional results on the Falcon dataset:

• Precision: ~0.9797
• Recall: ~0.9088
• mAP@0.5: ~0.9416
• mAP@0.5:0.95: ~0.8843

These scores are based on the YOLOv8 architecture.
For detailed logs and more metrics, see the models/logs/yolov8_observo/ directory.

---

📁 Project Structure

├── app/                   # Flask backend app
│   ├── backend.py
│   ├── routes.py
│   ├── simple_backend.py
│   ├── requirements.txt
│   └── templates/
│       └── index.html
├── config/
│   └── observo.yaml
├── data/
│   └── raw/
│       ├── classes.txt
│       ├── predict.py
│       ├── train.py
│       ├── visualize.py
│       ├── yolo_params.yaml
│       └── data/
├── docs/
│   └── report_outline.md
├── mobile/
│   ├── src/
│   │   ├── App.js
│   │   ├── api/
│   │   └── screens/
│   ├── package.json
│   ├── README.md
│   └── SETUP.md
├── models/
│   ├── weights/
│   └── logs/
├── notebooks/
│   ├── EDA.ipynb
│   └── train_yolov8.ipynb
├── src/
│   ├── detect.py
│   ├── train.py
│   ├── utils.py
│   └── constraints.txt
├── uploads/
├── Web_App_frontend/
│   ├── src/
│   │   ├── components/
│   │   ├── pages/
│   │   └── hooks/
│   ├── package.json
│   └── vite.config.ts
├── environment.yaml
├── requirements.txt
├── requirements_minimal.txt
├── render.yaml
├── gunicorn_config.py
├── Procfile
├── .gitignore
├── .gitattributes
├── DEPLOYMENT.md
└── README.md

---

⚠️ DO NOT COMMIT SENSITIVE OR LARGE FILES

• Model weights, logs, uploads, and raw data are excluded via .gitignore.
• Do NOT commit files in models/weights/, models/logs/, uploads/, or data/raw/.
• Notebooks and environment folders are also excluded.

---

🤝 Contributing

We welcome your contributions!

1. Fork the repository.
2. Create a branch for your changes.
3. Submit a pull request with a clear description.

For major changes or new features, please open an issue first to discuss.

---

📄 License

This project is licensed under the MIT License.
See the LICENSE file for details.

---

✨ Explore the universe with VISTA-S!
Star the repo, open issues, or contribute to its growth.
Your feedback and contributions are always welcome.