- New tools like AR glasses should attempt to supplement traditional tools like the guide dog and white cane that are relied on by millions of people instead of replacing them.
- While gathering physical information about nearby objects can be useful, identifying and gathering semantic information such as text is a frequent unmet need for blind users.
- The assisstant devices should not make additional noise and cover up environmental sounds since the sound is a valuable information source for blind people

University of Illinois at Urbana-Champaign

AR is a technology that augments physical environments on a mobile device screen by overlaying them with digital content. Unlike Virtual Reality(VR) that creates an immersive virtual environment, AR is based on a footprint of a real surrounding and it only adds additional computer-generated data. An AR glass is believed that can help people with vision impairment or people that are completely blind. 

Augmented Reality(AR) Glasses

Augmented Reality for Visually Impaired People

A study tested the potential of AR device in improving the functional vision of people with near-complete vision loss in 2018. An AR applicationthat translates spatial information into high-contrast visual patterns was developed. Performance was tested on a range of visual tasks. The result found that AR application was associated with improved accuracy and confidence in object recognition and in gesture recognition. 

Study of AR Glasses on Visual Impairment

Expected ideas on AR glasses 

- Object Localization: Identify the locations of the three sign poles using audio cues.
- Text Recognition:  Identify signs like "bus stop 52".
- Direct Navigation:   Walk to "bus stop 52."
- Text Recognition and Direct Navigation in Proximity Mode:  Switch to “proximity mode,” which would limit detection range but give the user a better indication of changing distance, then identify and walk to bus stop 80.

HoloLens AR Device Testing on Blind User

The researchers implement an intuitive user interface that each object in the environment has a voice and communicates with the user on command.  With minimal training, this system supports many aspects of visual cognition: obstacle avoidance, scene understanding, formation and recall of spatial memories, navigation.

Learn Before

Related