Smartphone-based obstacle detection for visually impaired people

A blind person walking in an unfamiliar environment faces many problems, this issue may be of identifying true obstacle or may be of identifying potholes, bumps in his way. In past few years, different types of ETA's have been developed for helping visually impaired people. Regardless of various ETA's available, they are still not affordable to the majority of blind people. And most of these ETA's only focuses on only one problem i.e. either pot-hole detection or obstacle in front of the user. Apart from that, they do not provide information about the environment in which user is present. This paper describes a real-time system which makes use of the ultrasonic sensor, camera, and smartphone for detection, recognition and processing of objects that hinders the path of visually impaired person. Ultrasonic sensors detect and measure the distance of obstacle while image captured from a camera is used for object recognition. The output given to the user is in the form of vibration and audio. The intensity of the output depends on the distance of an object from the user.