Undergraduate YPEC 2021

UG19-Walking Assistant for the Visually Impaired with Hand-Held LIDAR through Machine Learning

There are around 18000 people in Hong Kong who are visually impaired. Walking around in the streets is an essential part of their daily life. They need help in walking from one location to reach their destinations in a safe manner. An affordable and reliable technological solution will improve their personal safety and their quality of life. In this project, a LIDAR augmented mobile device which aids visually impaired people for day and night navigation has been developed and evaluated. The application includes navigation in the streets, obstacle warning and avoidance, falling detection and rescue. These functions are interacted through suitable user interface including voice-over and voice control. The navigation in the street function exploits the Global Positioning System (GPS) and assists users with voice guidance. The obstacle warning and avoidance function indicates to the user if the obstacles are detected within a close range during the navigation. The falling detection and rescue function keeps tracing the visually impaired people for falling accidents. When a falling action detected, the emergency call will be triggered for rescue immediately. The device can operate day and night under the uncongested area, and it can be attached to a walking stick or hanging on the neck. In general, the mobile application was found to improve the mobility of the visually impaired and their experience of walking in the street.