This project implements a real-time weapon detection system using the YOLOv8 model. The system is designed to detect and track weapons (specifically guns) within video streams or video files, providing a visual indication by highlighting detected weapons in each video frame.
- Model Used: YOLOv8, a state-of-the-art object detection model known for its speed and accuracy.
- Dataset: The model is trained on a dataset containing 6,000 annotated images focused on hand-held weapons.
- Dataset Link: Hand Weapon Dataset on Hugging Face
- Dataset Creation Tool: The dataset was curated and annotated using Roboflow, a popular tool for generating high-quality datasets.
- OpenCV: Utilized for video processing, frame handling, and drawing bounding boxes around detected objects.
- YOLOv8: Employed for its efficient object detection capabilities, enabling the system to identify weapons with high accuracy.
To get started, clone the repository and install the required dependencies:
git clone https://github.com/your-username/weapon-detection-system.git
cd weapon-detection-system
python main_area.py