Application of machine learning methods for traffic signs recognition

International Automobile Scientific Forum (IASF-2017) Intelligent Transport Systems

Filatov, D.V.^1 ; Ignatev, K.V.^1 ; Deviatkin, A.V.^1 ; Serykh, E.V.^1

V. Ulyanov (Lenin) St Petersburg State Electrotechnical University 'Leti', 5 Professora Popova Ul., St Petersburg

197376, Russia^1

关键词: Convolution neural network;    Illumination conditions;    Learning process;    Machine learning methods;    Morphological operations;    Real time modes;    Recognition rates;    Sequential images;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/315/1/012008/pdf
DOI  :  10.1088/1757-899X/315/1/012008

来源: IOP

【 摘 要 】

This paper focuses on solving a relevant and pressing safety issue on intercity roads. Two approaches were considered for solving the problem of traffic signs recognition; the approaches involved neural networks to analyze images obtained from a camera in the real-time mode. The first approach is based on a sequential image processing. At the initial stage, with the help of color filters and morphological operations (dilatation and erosion), the area containing the traffic sign is located on the image, then the selected and scaled fragment of the image is analyzed using a feedforward neural network to determine the meaning of the found traffic sign. Learning of the neural network in this approach is carried out using a backpropagation method. The second approach involves convolution neural networks at both stages, i.e. when searching and selecting the area of the image containing the traffic sign, and when determining its meaning. Learning of the neural network in the second approach is carried out using the intersection over union function and a loss function. For neural networks to learn and the proposed algorithms to be tested, a series of videos from a dash cam were used that were shot under various weather and illumination conditions. As a result, the proposed approaches for traffic signs recognition were analyzed and compared by key indicators such as recognition rate percentage and the complexity of neural networks' learning process.