Study on stairs detection using RGB-depth images

Soichiro Murakami, Manabu Shimakawa, Kimivasu Kivota, Takashi Kato

Abstract: Many visually impaired people have experienced walk accident, e.g., died due to falling down from station platform, injured on stairs. They need a support to walk safely. So there have been many researches that aim to be helpful for visually impaired to walk themselves in safety. This study aims to develop a walking-support-system that can detect steps and stairs for visually impaired. Previous studies only used depth sensor, such as Kinect or Xtion. That way was not available in outdoors because of sunlight. This paper presents the method that uses RGB-D camera to detect stairs and steps by using RGB images and depth images without regarding indoors and outdoors. The effectiveness of the proposed method will be shown with some results.