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 selfcalibrating 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 tradeoff between increased ease-of-use and slightly diminished accuracy of the jump height measurement.
Vertical jump height is an important tool to measure athletes' lower body power in sports science and medicine. Several different methods exist to measure jump height, but each has its own limitations. This work proposes a novel way to measure jump height directly, using optical tracking with a single smartphone camera. A parabolic fall trajectory is obtained from this video by tracking a single feature. The parabolic trajectory is then used to partially calibrate the camera and convert pixel measurements into real-world units, allowing the calculation of the achieved height. Comparison to an optical motion capture system yields promising results.
Introduction: In this work, we use simulated data to quantify the different failure mechanisms of a previously presented low-cost jump height measurement system, based on widely available consumer smartphone technology. Methods: In order to assess the importance of the different preconditions of the jump height measurement algorithm, we generate a synthetic dataset of 2000 random jump parabolas for 2000 randomly generated persons without real-world artifacts. We then selectively add different perturbations to the parabolas and reconstruct the jump height using the evaluated algorithm. The degree to which the manipulations influence the reconstructed jump height gives us insights into how critical each precondition is for the method’s accuracy. Results: For a subject-to-camera distance of 2.5 meters, we found the most important influences to be tracking inaccuracies and distance changes (non-vertical jumps). These are also the most difficult factors to control. Camera angle and lens distortion are easier to handle in practice and have a very low impact on the reconstructed jump height. The intraclass correlation value ICC(3,1) between true jump height and the reconstruction from distorted data ranges between 0.999 for mild and 0.988 for more severe distortions. Conclusion: Our results support the design of future studies and tools for accurate and affordable jump height measurement, which can be used in individual fitness, sports medicine, and rehabilitation applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.