A Framework for the Outdoor Wayfinding of Visually Impaired

Date & Time

Tuesday, March 19, 2024 - 11:20 AM PDT  

Location

Platinum 1  

Description

Wayfinding has been a critical component of self-sufficiency for people with disabilities. People with vision impairments still struggle with wayfinding, regardless of whether they are indoors or outdoors. Recent developments in satellite technology for outdoor areas (e.g., GPS) and the prevalence of smartphones enable precise tools for wayfinding and means to be used. However, numerous outdoor premises remain, such as sidewalks and office buildings, in and around university campuses, where there is limited (or sometimes non-existent) efficiency of satellite-based systems such as global positioning systems (GPS). Even in places with decent GPS coverage, the precision is typically insufficient for fine-grained pedestrian navigation. As such, this work emphasizes the need for auxiliary outdoor wayfinding tools for people with vision impairments through a user study and quantitative study of GPS accuracy in outdoor environments. This work presents PathLookup, a deep learning-based image localization framework for reliably giving path advancement information for outdoor wayfinding. PathLookup was very accurate and efficient during testing, indicating that it could be a helpful tool for future inclusion in outdoor wayfinding systems.

This Presentation Link is provided by the Presenter(s) and not hosted by the Center on Disabilities at CSUN. The Center on Disabilities has confirmed, as of April 18, 2024, content linked is relevant to the presentation, but has not been reviewed for accessibility nor will the Center on Disabilities attempt to remediate any accessibility issues in the linked content. Please contact the Presenter(s) with any accessibility concerns.

 

Audience

• Higher Education
• Disability Specific
• Research & Development

Audience Level

Intermediate  

Session Summary (Abstract)

This work presents the need for an auxiliary tool to assist visually impaired persons in outdoor wayfinding. As such, a computer vision-based framework will be presented that effectively provides path advancement information to a destination.  

Primary Topic

Blind/Low Vision  

Secondary Topics

• Artificial Intelligence (AI) & Machine Learning (ML)
• Independent Living
• Mobility

 

Session Type

Journal Track  

Presenter

• Uddipan Das
  The College of New Jersey

Add to Outlook/iCal (How it works)

Back to Session List