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
Self-Localization at Street Intersections. (2014). Self-Localization at Street Intersections. In Computer and Robot Vision (CRV), 2014 Canadian Conference on (pp. 40–47). IEEE.
Real-time walk light detection with a mobile phone. (2010). Real-time walk light detection with a mobile phone. In Computers Helping People with Special Needs (pp. 229–234). Springer Berlin Heidelberg.
Detecting and locating crosswalks using a camera phone. (2008). Detecting and locating crosswalks using a camera phone. In Computer Vision and Pattern Recognition Workshops, 2008. CVPRW'08. IEEE Computer Society Conference on (pp. 1–8). IEEE.
  • Collage of RERC staff mebers and RERC projects

    Rehabilitation Engineering Research Center

    The Center's research goal is to develop and apply new scientific knowledge and practical, cost-effective devices to better understand and address the real-world problems of blind, visually impaired, and deaf-blind consumers

    Read More
Current

Project Members

Giovanni Fusco Huiying Shen