September 2016
Volume 57, Issue 12
Open Access
ARVO Annual Meeting Abstract  |   September 2016
A mobile image enhancement system for sight impaired individuals
Author Affiliations & Notes
  • Iain Robert Wilson
    Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, Oxfordshire, United Kingdom
  • Joram Jacob Van Rheede
    Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, Oxfordshire, United Kingdom
  • Alex Michael Campbell
    Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, Oxfordshire, United Kingdom
  • Robert E MacLaren
    Nuffield Laboratory of Ophthalmology, University of Oxford, Oxford, United Kingdom
  • Stephen Lloyd Hicks
    Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, Oxfordshire, United Kingdom
  • Footnotes
    Commercial Relationships   Iain Wilson, None; Joram Van Rheede, None; Alex Campbell, None; Robert MacLaren, None; Stephen Hicks, None
  • Footnotes
    Support  Google Impact Challenge UK 2014
Investigative Ophthalmology & Visual Science September 2016, Vol.57, 1956. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to Subscribers Only
      Sign In or Create an Account ×
    • Get Citation

      Iain Robert Wilson, Joram Jacob Van Rheede, Alex Michael Campbell, Robert E MacLaren, Stephen Lloyd Hicks; A mobile image enhancement system for sight impaired individuals. Invest. Ophthalmol. Vis. Sci. 2016;57(12):1956.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Image enhancement techniques have been shown to provide improvements in functional sight in some visually impaired individuals where residual vision is present. Most studies reporting improvements are laboratory based controlled experiments and little is understood of the real world efficacy of these techniques and their effect on quality of life. We present a completely mobile platform for testing image enhancement algorithms and monitoring and assessing the benefit to visually impaired individuals in every-day uncontrolled situations.

Methods : We designed and implemented an aesthetically and ergonomically considered system, comprising of a headset and control unit. The headset combined a color and depth camera with a see-through high resolution 22 degree digital screen. The control unit contains a mobile processor running a set of highly optimised real-time image processing algorithms to maximise the visual saliency of nearby objects through distance estimation, edge detection and cartoonisation. Tactile interfaces on the control unit allow users and experimenters to change visualisation modes and parameters. Remote viewing and data access tools were developed to simplify user orientation and assessment.
The system was assessed in controlled conditions with 103 visually impaired participants with a range of conditions, including: macular degeneration, retinitis pigmentosa, cataracts and glaucoma. Participants performed orientation and mobility tasks involving identifying objects and people, free walking and hand-eye coordination.

Results : The system performed well in each two-hour assessment. Approximately 25% of participants experienced an objective improvement in functional vision with individuals with some degree of central vision experiencing the greatest improvements. The interface was intuitive and required minimal training, and the size and weight of the headset was well tolerated.

Conclusions : This system is a viable platform for simplifying further research into vision enhancing techniques for visually impaired people. Unsupervised “take-home” trials are currently underway to study real-life use, learning effects and ergonomics, using the presented system.

This is an abstract that was submitted for the 2016 ARVO Annual Meeting, held in Seattle, Wash., May 1-5, 2016.

 

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×