Presentation 2022-12-08
Walking support system for the visually impaired
Ryuta Sekine, shun-ichi yonemura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) According to the Metropolitan Police Department statistics, in 2021, 43.6% of all traffic accidents will involve bicycles. There are many bicycles running on the sidewalk, and especially for the visually impaired, the situation where the bicycle runs at high speed on the sidewalk is a threat that leads to serious injury. The purpose of this study is to identify risk factors that visually impaired encounter while walking on sidewalks, and to construct a walking support system that avoids such risks. First, we conducted an interview survey with visually impaired in order to understand the current situation of walking on sidewalks. As a result, on sidewalks that are adjacent to roads, the sound of bicycles running is masked by environmental sounds such as the noise of cars and crowds, which delays the timing of noticing an approaching bicycle, creating a dangerous situation. It turned out that he was caught. From this, we believe that if visually impaired can be made to recognize the presence of a bicycle at an early stage, collision accidents on sidewalks can be avoided. In this paper, we propose a system that uses image analysis to detect approaching bicycles on the sidewalk and uses vibration to notify the visually impaired of the approaching bicycles. We built a prototype system using YOLO and conducted verification experiments. As a result, it was suggested that a visually impaired could take action to avoid a collision with a vibration notification if the bicycle was traveling on a sidewalk at an average speed. I will report it.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) visually impaired / walking support / collision avoidance
Paper # WIT2022-8
Date of Issue 2022-11-30 (WIT)

Conference Information
Committee WIT / HI-SIGACI
Conference Date 2022/12/7(2days)
Place (in Japanese) (See Japanese page)
Place (in English) AIST Tokyo Waterfront (TBD)
Topics (in Japanese) (See Japanese page)
Topics (in English) Well-being Information Technology
Chair Shinji Sakou(Nagoya Inst. of Tech.)
Vice Chair Tomohiro Amemiya(Univ. of Tokyo)
Secretary Tomohiro Amemiya(Saitama Industrial Tech. Center) / (Teikyo Univ.)
Assistant Minako Hosono(AIST) / Aki Sugano(Nagoya Univ.) / Tomoyasu Komori(NHK)

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) Walking support system for the visually impaired
Sub Title (in English) Study of collision avoidance support system with bicycles on sidewalks
Keyword(1) visually impaired
Keyword(2) walking support
Keyword(3) collision avoidance
1st Author's Name Ryuta Sekine
1st Author's Affiliation Sibaura Institute of Technology(SIT)
2nd Author's Name shun-ichi yonemura
2nd Author's Affiliation Sibaura Institute of Technology(SIT)
Date 2022-12-08
Paper # WIT2022-8
Volume (vol) vol.122
Number (no) WIT-295
Page pp.pp.23-28(WIT),
#Pages 6
Date of Issue 2022-11-30 (WIT)