This project focuses on detecting industrial safety gear using a custom object detection model. The model was fine-tuned on a self-annotated dataset with specific safety gear classes. The annotations were created using LabelImg, and the model was trained using YOLOv8. The final model is capable of performing real-time detection via a webcam and processing video input using OpenCV.

• data/: Contains the custom dataset and annotations.
• models/: Directory to save the trained YOLOv8 model.
• output/: Contains the annotated sample output files
• training/detect/: Contains the model trained data and affiliated results.

• Custom Object Detection: Developed a model for detecting industrial safety gear using a self-annotated dataset.
• Real-time Detection: Integrated webcam-based real-time object detection.
• Video Processing: Used OpenCV for object detection in video files.
• Transfer Learning: Leveraged YOLOv8 for fine-tuning on the custom dataset.

1. Clone the repository:

   git clone https://github.com/yourusername/industrial-safety-gear-detection.git
   

2. Install the required dependencies :

   pip install -r requirements.txt
   

3. Open and run app.py file :

   python main.py
   

The custom dataset was annotated using LabelImg. It includes images of various industrial environments with annotated safety gear such as helmets, gloves, goggles and jacket.

If you’d like to contribute, please fork the repository and use a feature branch. Pull requests are welcome.

This project is licensed under the MIT License.