Skip to content

Seat Belt Detection using YOLO v5, v8, v9 for image processing course. Evaluate performance on a consistent dataset. Compare variations in YOLO models.

Notifications You must be signed in to change notification settings

HayaAbdullahM/Seat-Belt-Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

40 Commits
 
 
 
 
 
 

Repository files navigation

Seat Belt Detection

This repository contains implementations of Seat Belt Detection using YOLOv5, YOLOv8, and YOLOv9. The project is part of an image processing course aimed at evaluating the performance of different YOLO versions on a consistent dataset and comparing their variations.


Table of Contents


Introduction

Seat belt detection is crucial for ensuring road safety. By employing computer vision techniques, this project aims to automatically detect the presence or absence of seat belts in images. This not only aids in enforcing safety regulations but also promotes awareness among drivers and passengers.


Dataset

The dataset used for this project contains annotated images with various scenarios involving seat belts. This curated dataset ensures consistency across different YOLO model evaluations. You can access and download the dataset from here.


Main Branch

Description

The main branch serves as the primary branch of the project, containing stable and tested code. It provides a baseline implementation of the seat belt detection system using YOLOv5 as the default model.

Usage

To use the code from the main branch:

  1. Clone the repository:

    git clone https://github.com/HayaAbdullahM/Seat-Belt-Detection.git
  2. Install the necessary dependencies:

    pip install -r requirements.txt
  3. Run the seat belt detection system.


YOLOv5 Branch

Description

The YOLOv5 branch focuses on integrating and evaluating the YOLOv5 model for seat belt detection. It includes modifications and optimizations specific to YOLOv5 to enhance detection accuracy and speed.

Usage

To use the code from the YOLOv5 branch:

  1. Clone the repository:

    git clone https://github.com/HayaAbdullahM/Seat-Belt-Detection.git
  2. Switch to the YOLOv5 branch:

    git checkout Yolov5
  3. Install the necessary dependencies:

    pip install -r requirements.txt
  4. Train and evaluate the YOLOv5 model on the provided dataset.


YOLOv8 Branch

Description

The YOLOv8 branch introduces enhancements and modifications to the YOLO architecture to create a specialized version for seat belt detection. It aims to improve detection accuracy and speed compared to previous versions.

Usage

To use the code from the YOLOv8 branch:

  1. Clone the repository:

    git clone https://github.com/HayaAbdullahM/Seat-Belt-Detection.git
  2. Switch to the YOLOv8 branch:

    git checkout Yolov8
  3. Install the necessary dependencies:

    pip install -r requirements.txt
  4. Train and evaluate the YOLOv8 model on the provided dataset.


YOLOv9 Branch

Description

The YOLOv9 branch represents the latest advancements in the YOLO series, incorporating cutting-edge techniques and optimizations for seat belt detection. It aims to achieve superior performance in terms of accuracy, speed, and robustness.

Usage

To use the code from the YOLOv9 branch:

  1. Clone the repository:

    git clone https://github.com/HayaAbdullahM/Seat-Belt-Detection.git
  2. Switch to the YOLOv9 branch:

    git checkout Yolov9
  3. Install the necessary dependencies:

    pip install -r requirements.txt
  4. Train and evaluate the YOLOv9 model on the provided dataset.


Conclusion

Each branch in this repository focuses on a specific YOLO version tailored for seat belt detection. By comparing and analyzing the results from different branches, we gain insights into the strengths and weaknesses of each model, contributing to the advancement of computer vision techniques for road safety.


License

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

About

Seat Belt Detection using YOLO v5, v8, v9 for image processing course. Evaluate performance on a consistent dataset. Compare variations in YOLO models.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published