2019-063 – GymCam: Using a Camera to Detect, Recognize, and Track Multiple Repetitive Exercises Simultaneously

GymCam is a system for automatically detecting, recognizing and tracking multiple exercises simultaneously via a camera placed in the environment without any user intervention. All concurrently occurring exercises from other activities in the video are segmented, the type of each exercise is recognized, and the number of repetitions for each of them is counted. GymCam advances the field of real-time exercise tracking by filling some crucial gaps, such as tracking whole body motion, handling occlusion, and enabling single-point sensing for a multitude of users. Cindy Lou Chepanoske cchepano@andrew.cmu.edu 412-268-2979