Title :
Recognition of elevators with the Kinect cane system for the visually impaired
Author :
Kuramochi, Y. ; Takizawa, H. ; Aoyagi, M. ; Ezaki, N. ; Shinji, M.
Author_Institution :
Univ. of Tsukuba, Tsukuba, Japan
Abstract :
This paper proposes a method of recognizing elevators in corridor scenes by using our Kinect cane system for the visually impaired. The proposed method recognizes elevator doors by applying the RANSAC algorithm to depth data obtained by a Kinect sensor. The method is applied to actual corridor scenes that include various types of elevator. The experimental results indicate that the system is promising as a means of recognizing elevators in corridor scenes.
Keywords :
handicapped aids; haptic interfaces; lifts; object recognition; Kinect cane system; Kinect sensor; RANSAC algorithm; corridor scenes; elevator door recognition; random sample consensus; tactile device; visually impaired person; Color; Educational institutions; Elevators; Image edge detection; Organizations; Robot sensing systems;
Conference_Titel :
System Integration (SII), 2014 IEEE/SICE International Symposium on
Conference_Location :
Tokyo
Print_ISBN :
978-1-4799-6942-5
DOI :
10.1109/SII.2014.7028024