While deep convolutional networks gain overwhelming accuracy for computer vision, they are also well-known for their high computation costs and memory demands. Given limited resources, they are difficult to apply. As a consequence, it is beneficial to investigate small, lightweight, accurate deep convolutional neural networks (ConvNets) that are better suited for resource-limited electronic devices. This study presents qNet and sqNet, two small and efficient ConvNets for fast traffic sign recognition using uniform macro-architecture and depth-wise separable convolution. The qNet is designed with fewer parameters for even better accuracy. It possesses only 0.29M parameters (0.6 of one of the smallest models), while achieving a better accuracy of 99.4% on the German Traffic Sign Recognition Benchmark (GTSRB). The resulting sqNet possesses only 0.045M parameters (almost 0.1 of one of the smallest models) and 7.01M multiply-add computations (reducing computations to 30% of one of the smallest models), while keeping an accuracy of 99% on the benchmark. The experimental results on the GTSRB demonstrate that authors’ networks are more efficient in using parameters and computations.
Efficient convNets for fast traffic sign recognition
IET Intelligent Transport Systems ; 13 , 6 ; 1011-1015
2019-04-10
5 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
object detection , convolutional neural nets , sqNet possesses , German Traffic Sign Recognition Benchmark , computer vision , learning (artificial intelligence) , ConvNets , deep convolutional neural networks , fast traffic sign recognition , GTSRB , traffic engineering computing , image recognition , object recognition
Metadata by IET is licensed under CC BY 3.0
A Novel Deep ConvNets Architecture for Traffic Sign Recognition
Springer Verlag | 2022
|TRAFFIC SIGN RECOGNITION DEVICE AND TRAFFIC SIGN RECOGNITION METHOD
Europäisches Patentamt | 2023
|TRAFFIC SIGN RECOGNITION DEVICE AND TRAFFIC SIGN RECOGNITION METHOD
Europäisches Patentamt | 2017
|Efficient On-the-fly Category Retrieval Using ConvNets and GPUs
British Library Conference Proceedings | 2015
|