Traffic Sign Recognition based on Synthesised Training Data

Stergiou, Alexandros; Kalliatakis, Grigorios; Chrysoulas, Christos

Abstract

To deal with the richness in visual appearance variation found in real-world data, we propose to synthesise training data capturing these differences for traffic sign recognition. The use of synthetic training data, created from road traffic sign templates, allows overcoming the problems of existing traffic sing recognition databases, which are only subject to specific sets of road signs found explicitly in countries or regions. This approach is used for generating a database of synthesised images depicting traffic signs under different view-light conditions and rotations, in order to simulate the complexity of real-world scenarios. With our synthesised data and a robust end-to-end Convolutional Neural Network (CNN), we propose a data-driven, traffic sign recognition system that can achieve not only high recognition accuracy, but also high computational efficiency in both training and recognition processes.

• Journal Article Type: Article
• Acceptance Date: Jul 24, 2018
• Online Publication Date: Jul 27, 2018
• Publication Date: 2018-09
• Deposit Date: Feb 7, 2020
• Publicly Available Date: Feb 7, 2020
• Journal: Big Data and Cognitive Computing
• Print ISSN: 2504-2289
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 2
• Issue: 3
• Article Number: 19
• DOI: https://doi.org/10.3390/bdcc2030019
• Keywords: traffic sign recognition; synthetic data; dataset generator; CNNs
• Public URL: http://researchrepository.napier.ac.uk/Output/2543068