Presentation 2018-12-06
Detection of Tactile Paving Using Deep Learning
Tadahiro Oyama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A blind guide dog exists as a partner for the visually impaired people to walk safely in the city. However, it is insufficient for the number of visually impaired people who need guide dogs. Therefore, development of a walking support system that replaces guide dogs as soon as possible is desired. In this research, as a function of the walking support system, the purpose is to examine a method to detect the tactile paving for the visually impaired from the first-person video. In this paper, I report the result of attempted detection of tactile paving using YOLO.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) visually impaired people / tactile paving / YOLO
Paper # WIT2018-47
Date of Issue 2018-11-28 (WIT)

Conference Information
Committee WIT / HI-SIGACI
Conference Date 2018/12/5(2days)
Place (in Japanese) (See Japanese page)
Place (in English) AIST Tokyo Waterfront
Topics (in Japanese) (See Japanese page)
Topics (in English) Well-being Information Technology
Chair Chikamune Wada(Kyushu Inst. of Tech.)
Vice Chair Daisuke Wakatsuki(Tsukuba Univ. of Tech.)
Secretary Daisuke Wakatsuki(AIST) / (Nagoya Inst. of Tech.)
Assistant Manabi Miyagi(Tsukuba Univ. of Tech.) / Takeaki Shionome(Teikyo Univ.) / Takashi Handa(Saitama Industrial Tech. Center)

Paper Information
Registration To Technical Committee on Well-being Information Technology / *
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Detection of Tactile Paving Using Deep Learning
Sub Title (in English)
Keyword(1) visually impaired people
Keyword(2) tactile paving
Keyword(3) YOLO
1st Author's Name Tadahiro Oyama
1st Author's Affiliation Kobe City College of Technology(KCCT)
Date 2018-12-06
Paper # WIT2018-47
Volume (vol) vol.118
Number (no) WIT-341
Page pp.pp.83-85(WIT),
#Pages 3
Date of Issue 2018-11-28 (WIT)