Home > Archive > 2022 > Volume 12 Number 6 (Nov. 2022) >
IJMLC 2022 Vol.12(6): 328-332 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2022.12.6.1119

Support for Visually Impaired Persons' Understanding of Proximity Space and Action Recognition Based on Pointing

Yasuyuki Murai, Yumiko Ota, Hisayuki Tatsumi, and Masahiro Miyakawa

Abstract—It is essentially important for the visually impaired to accurately understand their surroundings. However, the only way for visually impaired people to understand their surroundings is by hearing and touch. In human support, a pointing operation is effective in which the supporter holds the hand of a visually impaired person and points his or her hand toward the surrounding object to indicate its position. The purpose of this research is to develop a system that assists visually impaired people in understanding their surroundings based on this pointing motion. In this report, we propose a system that uses wearable camera and AI to recognize what is around and corrects the veering tendency when a visually impaired person walks.

Index Terms—Visually impaired, veering tendency, deep learning, wearable camera.

Yasuyuki Murai and Yumiko Ota are with Nihon Pharmaceutical University, Tokyo, Japan (email: {murai, arisue-888}@nichiyaku.ac.jp).
Hisayuki Tatsumi and Masahiro Miyakawa are with Tsukuba University of Technology/Department, Ibaraki, Japan (email: tatsumi@cs.k.tsukubatech.ac.jp; mamiyaka@gmail.com).

[PDF]

Cite: Yasuyuki Murai, Yumiko Ota, Hisayuki Tatsumi, and Masahiro Miyakawa, "Support for Visually Impaired Persons' Understanding of Proximity Space and Action Recognition Based on Pointing," International Journal of Machine Learning and Computing vol. 12, no. 6, pp. 328-332, 2022.

Copyright @ 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

 

General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quarterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net
  • APC: 500USD


Article Metrics in Dimensions