Obstacle detection and avoidance system for visually impaired people

In this paper, we implemented a wearable system for visually impaired users which allows them to detect and avoid obstacles. This is based on ultrasound sensors which can acquire range data from objects in the environment by estimating the time-of-flight of the ultrasound signal. Using a hemi-spherical sensor array, we can detect obstacles and determine which directions should be avoided. However, the ultrasound sensors are only used to detect whether obstacles are present in front of users. We determine unimpeded directions by analyzing patterns of the range values from consecutive frames. Feedback is presented to users in the form of voice commands and vibration patterns. Our system is composed of an ARM9-based embedded system, an ultrasonic sensor array, an orientation tracker and a set of vibration motors with controller.