This repository contains the source code and resources related to the academic weapon detection project, developed as part of research in the area of computer security.
The main objective of this project is to design and implement an advanced system for the autonomous detection of firearms and knives. Using the YOLOv8 (You Only Look Once) framework and transfer learning techniques, we seek to improve security effectiveness through continuous, real-time surveillance.
-
YOLOv8 Framework: One implementation uses YOLOv8, known for its efficiency in real-time object detection.
-
Transfer Learning: Transfer learning techniques are employed to adapt the model to a specific context and improve accuracy in weapon detection.
-
Integration with IP Cameras: The system is designed for easy integration with IP cameras, allowing for real-time surveillance and immediate notifications.
https://universe.roboflow.com/joao-assalim-xmovq/weapon-2/dataset/2
- Repository Cloning:
git clone https://github.com/JoaoAssalim/Weapons-and-Knives-Detector-with-YOLOv8.git
- Installation of dependencies:
pip install -r requirements.txt
- System Execution:
python detecting-images.py
Contributions are welcome! If you encounter issues or have suggestions for improvement, please open an issue in this repository.
This project is part of academic research in the area of computer security. The results obtained and performance analyzes are documented in detail in the scientific article that will be made available in the future.
This project is distributed under the [MIT] license (LICENSE.md). See the LICENSE.md file for details.