JumpMetric: Assessment of Fiducial Positions for Vertical Jump Height Estimation from Depth Cameras and Wearable Sensors

Abstract

While the training of vertical jumps offers benefits for agility and performance across various amateur sports, the objective measurement of jump height remains a challenge compared to simpler assessments like the broad jump distance in a sand pit. We present and compare two approaches for the estimation of vertical jump height from an off-the-shelf depth camera and cost-efficient wearable motion sensors with an onboard accelerometer. With these, we assess the accuracy achievable at diverse fiducial positions, which are 7 skeletal joints and 10 wearing positions, respectively. A user study was conducted with 44 subjects (33 male, 11 female, 23.1 ± 2.2 years) performing countermovement jumps. From the simultaneous recordings of the two modalities, provided as a public dataset, the subjects' vertical jump height is estimated and compared to the manually determined ground truth. The most accurate values of the depth camera were obtained from the pelvis and thoracic spine joint with an average error of -15.8 ± 23.3 mm and 24.2 ± 35.1 mm, respectively. The best estimates from the wearable motion sensor data were obtained from the neck position and the ankles with an average error of 18.8 ± 29.0 mm and -4.8 ± 35.2 mm, respectively. The results demonstrate that, by selecting suitable and reliable fiducial positions, both modalities can successfully be used to estimate athletes' vertical jump height with easy-to-use and cost-efficient tools.