Design Research on the Application of YOLOv5-based Road Condition Detection in Assistive Devices for the Visually Impaired

Outdoor navigation has long been a wicked problem for the visually impaired. With the development of technologies, new designs with them are temping to deal with existing obstacles both from within and outside, but still leaving pain points to be solved. Driven by social considerations and user-centred perspectives, we propose an innovative and sustainable design framework for assistive devices catering to the visually impaired in this project. The core implementation layer utilizes Arduino, while the decision-making layer employs the YOLOv5 algorithm for object detection tasks, enabling hardware interaction in response to the detection results. The device successfully provides features such as environmental information feedback, tactile paving search and privacy intrusion warning, transforming necessary visual information into auditory and tactile feedback. By controlling it at a lower cost and simplifying interaction methods, our device offers essential mobility assistance to a broader range of visually impaired users.