Towards Seamless Sidewalk Navigation: On-Device Machine Learning for Real-Time Obstacle Detection in Visually Impaired Assistance

Zahiriddin Rustamov, Jaloliddin Rustamov, Medha Mohan Ambali Parambil, Soha Glal Ahmed, Sherzod Turaev

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Undeniably, visual impairment severely affects the quality of life and impacts many daily activities of visually impaired individuals. Visually impaired individuals have difficulty navigating on side-walks. There are many assistive tools available for navigational assistance for visually impaired individuals. The majority of assistive technologies for sidewalk navigation in visually impaired individuals rely on server-based models, introducing challenges of latency, data costs, and privacy. This research investigates on-device machine learning as an alternative, emphasizing real-time feedback and user experience. We assessed algorithms, including EfficientDet-Lite, SSD, and YOLOv4, optimizing them for mobile deployment. The resultant Android application, embedding the top-performing model, demonstrated the potential for immediate, server-independent feedback. This research not only bridges a notable gap in the literature but also paves the way for research on more accessible, immediate, and discreet navigation tools for the visually impaired community.

Original languageEnglish
Title of host publicationAdvancements in Smart Computing and Information Security - 2nd International Conference, ASCIS 2023, Revised Selected Papers
EditorsSridaran Rajagopal, Kalpesh Popat, Divyakant Meva, Sunil Bajeja
PublisherSpringer Science and Business Media Deutschland GmbH
Pages358-365
Number of pages8
ISBN (Print)9783031586033
DOIs
Publication statusPublished - 2024
Event2nd International Conference on Advances in Smart Computing and Information Security, ASCIS 2023 - Rajkot, India
Duration: Dec 7 2023Dec 9 2023

Publication series

NameCommunications in Computer and Information Science
Volume2037
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference2nd International Conference on Advances in Smart Computing and Information Security, ASCIS 2023
Country/TerritoryIndia
CityRajkot
Period12/7/2312/9/23

Keywords

  • assistive technologies
  • machine learning
  • obstacle detection
  • sidewalk
  • visually impaired

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Towards Seamless Sidewalk Navigation: On-Device Machine Learning for Real-Time Obstacle Detection in Visually Impaired Assistance'. Together they form a unique fingerprint.

Cite this