praveensunkara/Dog-Attack-Detection-Spy-YOLOv5
🐶 Dog-Attack-Detection-Spy-YOLOv5
A Raspberry Pi-based dog attack detection system powered by YOLOv5.
This solution helps in preventing dog attacks by:
- Detecting approaching/aggressive dogs
- Triggering an alarm sound to scare them away
- Sending the incident location via SMS using a GPS module
- This project is supported by the our patent! ---
🚀 System Deployment
- 🧠 Model: YOLOv5 (custom-trained)
- 📷 Hardware: Raspberry Pi 4 with Camera Module
- 📡 Sensors: GPS Module for location tracking
- 🔊 Output: Alarm + SMS alert to registered number
- 🧰 Code: Written in Python, optimized for edge devices
📸 Sample Detection Outputs
🐕 Dog Attack References
Due to frequent dog attacks, several people suffer injuries or die from rabies. The following images reflect real-world references.
<table> <tr> <td><img src="images/image1.jpg" width="250"/></td> <td><img src="images/image2.jpg" width="250"/></td> </tr> <tr> <td><img src="images/image3.jpg" width="250"/></td> <td><img src="images/image4.jpg" width="250"/></td> </tr> </table>
🧪 Prototype Setup & 📈 YOLOv5 Inference Output
These images show examples of YOLOv5 identifying potential dog attack scenarios and our physical prototype setup.
<table> <tr> <td><img src="images/image5.jpg" width="300"/></td> <td><img src="images/image6.png" width="300"/></td> <td><img src="images/image7.jpg" width="300"/></td> </tr> </table>
🎥 Demo Video
⚠️ GitHub does not support video autoplay. You can also view on YouTube for a better viewing experience.
🔗 Features at a Glance
🛠️ Installation & Usage
Follow the steps below to set up and run the Dog Attack Detection Streamlit app:
1️⃣ Clone the Repository
git clone https://github.com/praveensunkara19/Dog-Attack-Detection-Spy-YOLOv5.git
cd Dog-Attack-Detection-Spy-YOLOv5
2️⃣ Create and Activate a Virtual Environment (Recommended)
Create virtual environment (Windows):
python -m venv myenv
Activate the virtual environment:
myenv\Scripts\activate
3️⃣ Install Required Dependencies
pip install -r requirements.txt
✅ Ensure you have Python 3.8+ installed.
4️⃣ Run the Streamlit App
streamlit run app.py
The app will open automatically in your browser. You can:
Upload images/videos for detection
Try the built-in test image/video
View side-by-side results of predictions📦 Folder Structure
Dog-Attack-Detection-Spy-YOLOv5/ │ ├── images/ # Sample image outputs + demo video │ ├── image1.jpg │ ├── image2.jpg │ ├── image3.jpg │ ├── image4.jpg │ ├── image5.jpg │ ├── image6.png │ └── yolovideo.mp4 │ ├── test/ # Test input files │ ├── testimg.jpg │ └── testvideo.mp4 │ ├── yolov5_best.pt # Trained YOLOv5 model ├── app.py # Streamlit app ├── requirements.txt # Dependencies ├── README.md # Project documentation
📬 Contact
For issues, suggestions, or collaborations: 📧 Email Me: praveensunkara19@gmail.com 🔗 GitHub: praveensunkara19