Vision based guide-dog robot system for visually impaired in urban system

Abstract

This paper presents a research about a vision of guide-dog robot system for visually impaired people via the camera in smart phone. In this system, camera can replace blind people or visually impaired people's eyes to analyze the traffic situation. The recognition of traffic lights is proposed through the adaptive boosting (Adaboost) algorithm and template matching algorithm combined approach. Firstly, Adaboost method is applied for training the Pedestrian light signal detector and secondly by applying template matching algorithm to distinguish the traffic lights between green and red. And vanishing point is applied for zebra-crossing detection, and histogram is applied to defend the misrecognition and separate real zebra-crossing from staircase.