Wearable computer vision enhances independence and reduces, by 37%, the risk of collision for people who are blind or visually impaired and use a long cane or guide dog for assistance, according to findings from a randomised controlled trial.
Often marketed as reducing the risk of a fall, until now there has been little evidence of the devices’ effectiveness in daily mobility settings.
The trial, led by vision rehabilitation researchers at Mass Eye and Ear, and published in JAMA Ophthalmology, used a device and data recording unit enclosed in a sling backpack with a chest-mounted, wideangle camera on the strap, and two Bluetooth-connected wristbands worn by the user.
The camera, connected to a processing unit, captured images and analysed collision risk based on the relative movement of incoming and surrounding objects in its field of view. If an imminent collision was detected on the left or right side, the corresponding wristband would vibrate, and a head-on collision would cause both wristbands to vibrate. The device analysed relative motion, warning only of approaching obstacles that posed a collision risk, and ignoring objects not on a collision course.
Alex Bowers, PhD, a clinical researcher and one of the co-authors of the paper, said “Long canes are still very helpful and cost-effective tools that work well in many situations, but we hope a wearable device like this can fill in the gaps that the cane might miss, providing a more affordable, easier to obtain option than a guide dog” .
