The article provides an overview of wearable devices that improve the quality of user recognition of objects of the surrounding world, reveals the process of developing an intelligent module for recognizing objects of urban infrastructure for "sound glasses" - a device designed for blind users. The functionality of the module under development, its architecture is characterized, the process and results of neural network training for object recognition are described, and an algorithm for identifying the color of traffic lights is given. The results of testing the developed software module are presented. The software module created in this work is an integral component of a fully functioning device "sound glasses", the use of which will allow people with visual disabilities to get information about events and the surrounding environment and navigate even in an unfamiliar environment.

Keywords: computer vision, neural network, smart glasses, sound glasses, visually impaired, YOLOv5, object recognition