Development of road sign detection using deep learning

Mohd Fadzil, Nur Fatin Nazihah (2024) Development of road sign detection using deep learning. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

Text (Full text) Development of road sign detection using deep learning.pdf - Submitted Version Download (1MB)

Abstract

Road sign detection plays a crucial role in intelligent transportation systems, aiding drivers in making informed decisions and enhancing overall road safety. In this project, we propose a robust road sign detection and recognition framework using deep learning techniques. The objective is to develop an intelligent system that can accurately detect and classify road signs from real-time video streams or images captured by onboard cameras. The proposed framework leverages the power of deep convolutional neural networks (CNNs) to learn discriminative features from road sign images. The model is trained on a comprehensive dataset of annotated road signs to improve its detection accuracy through pre-processing techniques, data augmentation, and fine-tuning. In addition to detection, the framework incorporates a recognition module that utilizes deep learning algorithms to classify the detected road signs into their respective categories. This enables the system to provide additional contextual information to drivers, such as speed limits, warnings, and other regulatory signs. The proposed road sign detection and recognition framework holds significant potential for integration into intelligent driver assistance systems, autonomous vehicles, and smart city applications. Enhancing the perception capabilities of vehicles can contribute to safer roads and more efficient transportation systems.

Actions (login required)

View Item