News
Capturing Blind People’s Movements to Improve Safety
Autonomous vehicles are trained on datasets to detect human movement in order to prevent collisions. However, these datasets often only include the movements of sighted individuals. Blind people often use canes to feel around for curbs and bumps, and these movements may not be interpreted properly by current autonomous vehicles, leading to potential life-threatening situations for Blind individuals. So, TRACE’s Dr. Hernisa Kacorri and Boston University College of Engineering Assistant Professor Eshed Ohn-Bar created BlindWays, a dataset of 3D motion captures of Blind individuals. This dataset can be used to train artificial intelligence models and improve the safety of walking around streets.
Read more about this amazing work in Capturing How Blind Pedestrians Navigate Their Environments to Expand Accessibility and Autonomous Cars Don’t Understand How Blind People Move Around. A Research Team Is Trying to Boost Safety.
