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.
CITATION STYLE
Yamanaka, Y., Kayukawa, S., Takagi, H., Nagaoka, Y., Hiratsuka, Y., & Kurihara, S. (2022). One-Shot Wayfinding Method for Blind People via OCR and Arrow Analysis with a 360-Degree Smartphone Camera. In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST (Vol. 419 LNICST, pp. 150–168). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-94822-1_9
Mendeley helps you to discover research relevant for your work.