Measuring vertical jump height using a smartphone camera with simultaneous gravity-based calibration

Abstract

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.

Markerless camera-based vertical jump height measurement using OpenPose

“…This work extends the method proposed by Webering et al [17], which determines jump height by analyzing the free-fall parabola of the jump in a high-speed video. Their algorithm is based on the principle that the vertical offset of a body's center of mass (CoM) describes a parabola over time while it is in free fall.…”

“…All of these works use parabolic trajectories of falling or bouncing objects to calculate the intrinsic and extrinsic camera parameters of one or multiple cameras. However, in contrast to these works, the algorithm proposed by Webering et al [17] simplifies the calibration problem to a single degree of freedom-the camera-to-subject distance-by placing a few constraints on the experimental setup. This allows the reconstruction of an absolute scale and calculation of the jump height from a single free-fall parabola.…”

“…The jump height calculation algorithm proposed by Webering et al [17] consists of 6 steps, which are summarized here.…”

“…• Analyzing the free-fall parabola of a feature in a highspeed video. -Requires markers applied directly on skin [17].…”

Machine learning aided jump height estimate democratization through smartphone measures

“…Estimating jump height using SP-embedded IMU direct measures has not been attempted, to the best of our knowledge, aside from preliminary investigations forerunner of the current one ( 22 , 23 ). SP-focused studies were all based on video camera-based approaches ( 24 , 25 ). Among the alternatives available on the market, the most commonly used SP application is MyJump, whose reliability has been tested in several studies ( 26 – 32 ).…”