UC Santa Cruz

We introduce WeAllWalk, a data set of inertial sensor time series collected from blind and sighted walkers using a long cane or a guide dog. Ten blind volunteers (seven using a long cane, one using a guide dog, and two alternating use of a long cane and of a guide dog) as well as ve sighted volunteers contributed the data collection. The participants walked through fairly long and complex indoor routes that included obstacles to be avoided and doors to be opened. Inertial data was recorded by two iPhone 6s carried by our participants in their pockets and carefully annotated. Ground truth heel strike times were measured by two small inertial sensor units clipped to the participants’ shoes. We also present an in-depth comparative analysis of various step counting and turn detection algorithms as tested on WeAllWalk. This analysis reveals interesting differences between the achievable accuracy of step and turn detection across di erent communities of sighted and blind walkers.