Traffic sign detection and classification is a critical component of intelligent transportation systems, which is applied to inform automatic unmanned driving systems and driving assistance systems about conditions and limits of roads. Although computer vision is widely utilised in traffic sign detection, detection and recognising traffic signs globally remains a great challenge due to the variety of sign types, scale-variance and geometric variations. To address these problems, this study proposes a region-based deep convolutional neural network (CNN) framework for traffic sign detection and classification. Specifically, a multi-branch sample pyramid module is proposed, which is based on multi-branch CNNs for multi-scaled feature exaction. A limited deformable convolutional module is then embedded into the CNN layers to learn the distorted information representation for deformation handing. Moreover, a scale-aware multi-task region proposal network module is applied to detect traffic signs with various scales. The whole network is trained in an end-to-end manner. Finally, experiments are conducted on two public detection data sets to demonstrate the effectiveness of the proposed method.
Scale-aware limited deformable convolutional neural networks for traffic sign detection and classification
IET Intelligent Transport Systems ; 14 , 12 ; 1712-1722
2020-10-13
11 pages
Article (Journal)
Electronic Resource
English
object detection , image classification , sign types , computer vision , recognising traffic signs , learning (artificial intelligence) , scale-aware multitask region proposal network module , driving assistance systems , traffic sign detection , neural nets , road traffic , traffic engineering computing , feature extraction , deformable convolutional neural networks , region-based deep convolutional neural network framework , driver information systems , automatic unmanned driving systems
Metadata by IET is licensed under CC BY 3.0
Convolutional Neural Networks for Traffic Sign Recognition
TIBKAT | 2021
|Real-Time Traffic Sign Recognition Using Convolutional Neural Networks
Springer Verlag | 2021
|Enhancing the robustness of the convolutional neural networks for traffic sign detection
SAGE Publications | 2022
|Traffic Sign Classification with a Convolutional Network
British Library Online Contents | 2018
|