A real-time traffic sign recognition system for autonomous vehicle using Yolo / Nurul Paudziah Aida Mohd Paudzi
In recent years, research towards Autonomous Vehicle (AV) has grown up tremendously. The introduction of Advanced Driving Assistance System (ADAS) in AV has led researchers to explore on the key functionalities that an AV should have, proposes to create a convenience and safe environment where there...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/35625/1/35625.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In recent years, research towards Autonomous Vehicle (AV) has grown up tremendously. The introduction of Advanced Driving Assistance System (ADAS) in AV has led researchers to explore on the key functionalities that an AV should have, proposes to create a convenience and safe environment where there is no input acquire from a human throughout the journey. The key functionalities are including traffic sign recognition, parking space detection, pedestrian crash avoidance and blind spot detection. As the rises of road accident due to drivers’ carelessness and the distracted drivers that has been neglected the traffic signs on the road, this project aims to develop a traffic sign recognition system that can recognize in real-time for integrated on autonomous vehicles and to test the accuracy of the system. The image processing technique has been chosen to be applied on developing this system where the project is the implementation of the deep learning technology using You Only Look Once (YOLO) algorithm to train the model for detection. Five types of warning sign including crossroad, crossroad right, crossroad left, school children crossing and hump from Malaysian Traffic Sign is used. System testing was also conducted to study the accuracy of the detection and recognition towards traffic signs on the road. Test results reached real-time object detection with 96% accuracy on both traffic sign detection and recognition. The finding from this study is believed to be helpful as it may contribute to the automotive industry. In future, this system can be improved by integrating with the navigation system such as Global Positioning System (GPS) to make the system more functional and achieve more advance monitoring. |
|---|