Road Sign Recognition Project Based on YOLOv5 (YOLOv5 GUI)

English | 简体中文

训练策略

This is a road sign recognition project based on YOLOv5, developed with a PyQt5 interface, YOLOv5 trained model, and MySQL database. The project consists of five modules: parameter initialization, sign recognition, database, data analysis, and image processing(Please refer to the Chinese document for details).

Screenshots

• Sign Recognition Module

  

• Image Processing and Data Augmentation Module

  

• Parameter Initialization Module

  

• Database Module

  

• Data Analysis Module

  

• Login Interface

  

Video Demo

Road Sign Recognition System Based on YOLOV5

Getting Started

Run main.py.

Account and Password

Here are the default login credentials:

Username	Password
admin	123456
1	2

Modify the main function in main.py to enter the system directly without authentication.

Project Structure

• pt folder: Contains the YOLOv5 model file best.pt for road sign recognition.
• main_with folder: Contains login.py for the login UI and win.py for the main UI.
• dialog folder: Contains the RTSP pop-up interface.
• apprcc_rc.py: The resource file for the project.
• login_ji.py: Implements the login logic for the UI.
• run/run-exp52: The YOLOv5 road sign recognition model trained for 300 epochs.
• utils/tt100k_to_voc-main folder: Tool for converting JSON annotations to YOLO format.
• result: Folder to save inference results.
• run: Folder to save training logs and outputs.
• Dataset: Download from TT100k : Traffic-Sign Detection and Classification in the Wild.
• Database files: Located in the data folder, see -regn_mysql.sql for setup.

Install Dependencies

To install the required dependencies, run:

pip install -r requirements.txt

Attention

This project uses YOLOv5 v6.1.

For database connections, you need to set up your MySQL database as per the configurations below:

def get_db_connection():
    return pymysql.connect(
        host='localhost',
        user='root',
        password='123456',
        database='traffic_sign_recognition'
    )

There are two identical database links in the code that need to be modified, please check the database sql file under the data folder to establish the test database

Acknowledgements

• For converting the TT100K dataset to VOC format and selecting more than 100 images and XMLs for each category, see this CSDN blog post.
• The PyQt5-YOLOv5 integration was inspired by this GitHub repository.

Star History

Track the GitHub star history of this project: