Advancing Vertical Jump Analysis with Markerless Technology
Author Information
Author(s): Aleksic Jelena, Mesaroš David, Kanevsky Dmitry, Knežević Olivera M., Cabarkapa Dimitrije, Faj Lucija, Mirkov Dragan M.
Primary Institution: Faculty of Sport and Physical Education, University of Belgrade, Serbia
Hypothesis
The markerless MMPose-based system will demonstrate high agreement with the force plate in calculating key temporal and kinematic variables during the countermovement jump.
Conclusion
The MMPose-based markerless system is a reliable and cost-effective alternative to force plates for analyzing vertical jump performance.
Supporting Evidence
- The markerless system showed a very high correlation (r = 0.992) with force plate measurements.
- High reliability was observed for key performance metrics, with ICC values exceeding 0.9.
- Mean differences between the two systems were small, indicating functional comparability.
- The study validated the use of a smartphone-based system for detailed jump analysis.
- Participants were physically active individuals with no recent history of lower limb injuries.
- Statistical methods included Bland–Altman analysis and paired samples t-tests.
Takeaway
This study shows that a smartphone app can accurately measure how high people jump, making it easier for coaches and athletes to track performance without expensive equipment.
Methodology
Twelve participants performed countermovement jumps while data was collected using both a markerless system and force plates, with various performance metrics analyzed.
Potential Biases
Potential biases may arise from the reliance on computer vision algorithms for phase detection in jumps.
Limitations
The study's sample size may limit the generalizability of the findings, and the accuracy of the markerless system was tested only in a specific jump task.
Participant Demographics
Participants were 12 healthy, physically active individuals, including 7 males and 5 females, with an average age of 25.6 years.
Statistical Information
P-Value
0.005
Confidence Interval
95% CI: −0.071 to 0.293
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website