Development of a mobile app for road marking and traffic sign identification

• Main Author: Tan, Marilyne Ying Xuan
• Other Authors: Ng Beng Koon
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/167620
• Institution: Nanyang Technological University

In today’s world, the increasing prevalence of technology and artificial intelligence has provided opportunities to ensure people’s safety in various ways. One such application would be the use of deep learning, a subset of Artificial Intelligence, in the development of mobile application to address the issue of road safety. Road safety is a major concern around the world, and the identification of road markings and traffic signs plays a crucial role in ensuring safe driving. Therefore, the aim of this project is to develop a mobile application that accurately identifies road markings and traffic signs in real-time by leveraging on deep learning techniques. The application, developed on Android Studio and trained with a YOLOv5 model, utilizes the built-in camera in mobile devices to detect, classify, and predict these signs and markings, providing drivers with accurate and timely information to make informed decisions and reduce the risk of accidents. The model achieved an average accuracy of 94% in real-time detection for all the classes. This project contributes to the field of computer vision and has potential applications in the transportation industry. To enhance the application’s functionality, future improvements could include expanding the dataset and incorporating additional features.