Markerless camera-based vertical jump height measurement using OpenPose

Abstract

Vertical jump height is an important tool to measure athletes’ lower body power in sports science and medicine. This work improves upon a previously published self-calibrating algorithm, which determines jump height using a single smartphone camera. The algorithm uses the parabolic fall trajectory obtained by tracking a single feature in a high-speed video. Instead of tracking an ArUco marker, which must be attached to the jumping subject, this work uses the OpenPose neural network for human pose estimation in order to calculate an approximation of the body center of mass. Jump heights obtained this way are compared to the reference heights from a motion capture system and to the results of the original work. The result is a trade-off between increased ease-of-use and slightly diminished accuracy of the jump height measurement.