Authors:
Alexander Shustanov
and
Pavel Yakimov
Affiliation:
Samara National Research University, Russian Federation
Keyword(s):
TensorFlow, Convolutional Neural Networks, Traffic Sign Recognition, Image Processing, Computer Vision, Mobile GPU.
Related
Ontology
Subjects/Areas/Topics:
Image and Video Processing, Compression and Segmentation
;
Multimedia
;
Multimedia Signal Processing
;
Neural Networks, Spiking Systems, Genetic Algorithms and Fuzzy Logic
;
Telecommunications
Abstract:
In recent years, the deep learning methods for solving classification problem have become extremely popular.
Due to its high recognition rate and fast execution, the convolutional neural networks have enhanced most of
computer vision tasks, both existing and new ones. In this article, we propose an implementation of traffic
signs recognition algorithm using a convolution neural network. Training of the neural network is
implemented using the TensorFlow library and massively parallel architecture for multithreaded
programming CUDA. The entire procedure for traffic sign detection and recognition is executed in real time
on a mobile GPU. The experimental results confirmed high efficiency of the developed computer vision
system.