Computer vision-based terrain sensors for blind wheelchair users

We demonstrate computer vision techniques designed to aid blind or severely visually impaired wheelchair users. These techniques will be used to sense important features in nearby terrain from images collected by cameras mounted rigidly to the wheelchair. They will assist in the detection of hazards such as obstacles and drop-offs ahead of or alongside the chair, as well as detecting veer, finding curb cuts, finding a clear path, and maintaining a straight course. The resulting information is intended ultimately to be integrated with inputs from other sensors and communicated to the traveler using synthesized speech and/or audible tones and tactile cues, supplementing rather than replacing the user's existing cane, guide dog and wayfinding skills.