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.
Highlights
Traffic sign classification has been a challenging field in both academia and industry, with the latter receiving high interest
One of these first systems was introduced in Ciresan et al [12] and described a method that combines the outputs of multiple deep neural networks, called Multi-Column Deep Neural Networks (MCDNN)
The need for a more advanced activation layer derives from the shortcomings of the standard Rectified Linear Units (ReLU) activation function, which has proven to be very sensitive during training
Summary
Traffic sign classification has been a challenging field in both academia and industry, with the latter receiving high interest Applications of such systems can range from urban environment understanding, to being an integral part of Advance Driver Assistance Systems (ADAS) [1,2]. The German Traffic Sign Recognition Benchmark [4] is composed of 43 distinct classes and approximately 50,000 images that were extracted from 10 h of video, with a frame rate of 25 fps Another instance, where manual work was required to construct the dataset, was an image segmentation and road sign detection and classification system using SVMs for Spanish signs introduced in Timofte et al [5].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
