Home // IARIA Congress 2022, The 2022 IARIA Annual Congress on Frontiers in Science, Technology, Services, and Applications // View article


A Camera-Vision-based Indoor Navigation and Obstacle Avoidance Wearable Assistive Device for Visually Impaired People

Authors:
Wei-Jen Lin
Mu-Chun Su
Chun-Hsiang Cheng
Cheng-Yu Tsai
Yi-Hsin Chen

Keywords: visually impaired people; indoor navigation; object detection

Abstract:
In the past, if visually impaired people needed to go to an unknown/unfamiliar environment they had never been before, they had to rely on the assistance of relatives and friends and unavoidably caused troubles for both visually impaired people and their helpers. In this paper, we present a wearable assistive device to aid the visually impaired people. We use YOLOv5 to detect signages and CRNN to recognize texts embedded in the detected signages. Via a stereo camera, our system can help visually impaired people independently move in unknown environments. In addition, MobileNet was used to detect uneven pavements in front of visually impaired people to alert them whenever dangerous conditions exist on the road.

Pages: 45 to 48

Copyright: Copyright (c) IARIA, 2022

Publication date: July 24, 2022

Published in: conference

ISBN: 978-1-68558-017-9

Location: Nice, France

Dates: from July 24, 2022 to July 28, 2022