The article is devoted to the automatic detection and recognition of traffic signs system design which processes the images received from the vehicle digital video recorder. The digital video recorder is used both for its intended purpose and to include it in the process of driving, facilitating the driver's work and, thus, significantly increasing safety and driving comfort. The analysis of the solution of the problem of detection and recognition of traffic signs based on the use of convolutional neural networks is carried out. It is shown that the greatest advantage from the point of view of the criteria of accuracy and speed of response has the single shot multibox detector method. The learning of neural network is done based on traffic signs (adopted in Ukraine) learning sample The study showed that the proposed approach for all used datasets gave both the best recognition quality and maximum performance.