TY - GEN
T1 - One-Shot Wayfinding Method for Blind People via OCR and Arrow Analysis with a 360-Degree Smartphone Camera
AU - Yamanaka, Yutaro
AU - Kayukawa, Seita
AU - Takagi, Hironobu
AU - Nagaoka, Yuichi
AU - Hiratsuka, Yoshimune
AU - Kurihara, Satoshi
N1 - Funding Information:
We would like to thank all participants who took part in our user study. We would also thank Japan Airport Terminal Co., Ltd. and East Japan Railway Company. This work was supported by AMED (JP20dk0310108, JP21dk0310108h0002), JSPS KAKENHI (JP20J23018), and Grant-in-Aid for Young Scientists (Early Bird, Waseda Research Institute for Science and Engineering, BD070Z003100).
Funding Information:
Acknowledgments. We would like to thank all participants who took part in our user study. We would also thank Japan Airport Terminal Co., Ltd. and East Japan Railway Company. This work was supported by AMED (JP20dk0310108, JP21dk0310108h0002), JSPS KAKENHI (JP20J23018), and Grant-in-Aid for Young Scientists (Early Bird, Waseda Research Institute for Science and Engineering, BD070Z003100).
Publisher Copyright:
© 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.
PY - 2022
Y1 - 2022
N2 - We present a wayfinding method that assists blind people in determining the correct direction to a destination by taking a one-shot image. Signage is standard in public buildings and used to help visitors, but has little benefit for blind people. Our one-shot wayfinding method recognizes surrounding signage in all directions from an equirectangular image captured using a 360-degree smartphone camera. The method analyzes the relationship between detected text and arrows on signage and estimates the correct direction toward the user’s destination. In other words, the method enables wayfinding for the blind without requiring either environmental modifications (e.g. Bluetooth beacons) or preparation of map data. In a user study, we compared our method with a baseline method: a signage reader using a smartphone camera with a standard field of view. We found that our method enabled the participants to decide directions more efficiently than with the baseline method.
AB - We present a wayfinding method that assists blind people in determining the correct direction to a destination by taking a one-shot image. Signage is standard in public buildings and used to help visitors, but has little benefit for blind people. Our one-shot wayfinding method recognizes surrounding signage in all directions from an equirectangular image captured using a 360-degree smartphone camera. The method analyzes the relationship between detected text and arrows on signage and estimates the correct direction toward the user’s destination. In other words, the method enables wayfinding for the blind without requiring either environmental modifications (e.g. Bluetooth beacons) or preparation of map data. In a user study, we compared our method with a baseline method: a signage reader using a smartphone camera with a standard field of view. We found that our method enabled the participants to decide directions more efficiently than with the baseline method.
KW - Arrow detection
KW - OCR
KW - Signage
KW - Visual impairment
UR - http://www.scopus.com/inward/record.url?scp=85125234029&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125234029&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-94822-1_9
DO - 10.1007/978-3-030-94822-1_9
M3 - Conference contribution
AN - SCOPUS:85125234029
SN - 9783030948214
T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
SP - 150
EP - 168
BT - Mobile and Ubiquitous Systems
A2 - Hara, Takahiro
A2 - Yamaguchi, Hirozumi
PB - Springer Science and Business Media Deutschland GmbH
T2 - 18th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2021
Y2 - 8 November 2021 through 11 November 2021
ER -