This project aims to develop a wearable platform that enables the generation of a three dimensional (3D) model of the human skeleton and tracking its motion. There exist techniques that use depth cameras and special image processing software to model motion of the human skeleton, and Microsoft Kinect is a well-known example. However, the techniques using fixed cameras need to deploy camera devices at fixed locations in order to sense human motions. While this may be suitable for indoor fixed scenarios, it is not feasible for outdoor ubiquitous scenarios. Instead, the wearable platform from this project works for both scenarios.
This wearable platform is designed using a conductive stretchable fabric that is comfortable to wear. To estimate 3D body motions using the wearable platform, the model of the body skeleton needs to be fused with the bend angles of major joints on the skeleton. This project exploits the fabric's conductive resistance change to infer user dependent bend angles of body joints that the fabric covers. Furthermore, a 3D motion estimation method is developed for the platform that optimizes motion estimation results with body kinematics constraints.
Being comfortable for long-term wear and able to provide high motion sensing accuracy, this wearable platform will largely enhance the current practice of healthcare, sports, and outdoor entertainment. Benefits to senior residents and local retirement communities will be delivered through collaboration with the Center for Excellence in Aging and Geriatric Health. The research will be integrated into three undergraduate and graduate courses. Open houses will provide hands-on opportunities to a diverse group of minority students and high school students.
Data from this project includes human-subjects data, experiment results, software code, and curriculum materials. Data collection and management will be under the supervision of the Protection of Human Subjects Committee at William & Mary. Data will be stored securely on computers and regularly backed-up at William & Mary. The project web site is http://gzhou.blogs.wm.edu/nsf-eager-18/ , and the project web server is maintained and achieved by William & Mary. Data will be preserved for at least three years beyond the award period.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
