A Navigation System for Visual Impaired People Based on Object Detection

Abstract

Object detection technology has a great development in recent years. Many object recognition algorithms which can realize real-time object detection are proposed and implemented. Such technology is wildly used in various fields. In this paper, we discuss how to apply the object detection technology to support the outdoor movements of visual impaired people. Our proposed system will detect the users’ environment when the users are moving. According to the detecting result, our system will help users to avoiding potential dangers on their paths. In this paper, we focus on discussing the possible problems when we design such a system. Such kind of system will integrate the necessary technologies to realize the assistant function. In this paper, we use YOLOv5, RICOH R Development Kit (360-degree camera), Google map to compose our system.