Virtual aerial view of intersection area near a pedestrian's feet, reconstructed by Crosswatch algorithms

Crosswatch

Crosswatch is a smartphone-based system developed for providing real-time guidance to blind and visually impaired travelers at traffic intersections. Using the smartphone's built-in camera and other sensors, Crosswatch is designed to tell blind and visually impaired travelers what kind of traffic intersection they are near, how to align themselves properly to the crosswalk, and when the walk light or other traffic light indicates it is time to cross.

Click here for link to zip file containing Crosswatch code (open source) and documentation.

Tabs

Conference Papers
Ahmetovic, D., Manduchi, R., Coughlan, J., & Mascetti, S.. (2015). Zebra Crossing Spotter: Automatic Population of Spatial Databases for Increased Safety of Blind Travelers. In ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2015). http://doi.org/http://dx.doi.org/10.1145/2700648.2811392
Fusco, G., Shen, H., & Coughlan, J.. (2014). Self-Localization at Street Intersections. In Computer and Robot Vision (CRV), 2014 Canadian Conference on (pp. 40–47). IEEE.
Fusco, G., Shen, H., Murali, V., & Coughlan, J.. (2014). Determining a Blind Pedestrian’s Location and Orientation at Traffic Intersections. In Computers Helping People with Special Needs (pp. 427–432). Springer International Publishing.
Coughlan, J., & Shen, H.. (2012). The crosswatch traffic intersection analyzer: a roadmap for the future. In Computers Helping People with Special Needs (pp. 25–28). Springer Berlin Heidelberg.
  • L to R: Huiying Shen, Ali Cheraghi, Brandon Biggs, James Coughlan, Charity Pitcher-Cooper, Giovanni Fusco

    Coughlan Lab

    The goal of our laboratory is to develop and test assistive technology for blind and visually impaired persons that is enabled by computer vision and other sensor technologies.

    Read More