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.