aiqbench analysis
This paper bridges the gap between theoretical Human Pose Estimation (HPE) and practical sports application by surveying real-time algorithmic trade-offs and delivering a lightweight MediaPipe-based prototype. It provides engineers and sport scientists with a concrete blueprint for deploying markerless motion tracking systems that balance inference latency, frame rate, and positional accuracy without heavy computational overhead. Future work directions highlighted include integrating additional sensors and AR/VR to enhance the utility of these real-time feedback loops for non-expert users.
Integrated Real-Time Motion Tracking and AI Analysis for Athletic Performance Optimization
arXiv:2606.09842v1 Announce Type: cross Abstract: Applying Human Pose Estimation (HPE) in real world environments remains a challenging task, this paper explores and surveys real time HPE approaches and their limitations in sports analysis for individuals, alongside developing a practical lightweight prototype for real world testing and usage. The older marker-based motion capture systems evolving to the modern accessible and adaptable markerless deep learning approaches, this survey explores the foundational architectures, which balance precision and efficiency. We also compare algorithmic frameworks (top-down, bottom-up, one-stage approaches, etc.) on practical deployment metrics such as inference latency, frame rate, mean per-joint position error, and temporal jitter to guide model selection process for sports application. As our prime contribution, we are proposing a modular, lightweight software prototype, which uses MediaPipe HPE framework with multiple exercise specific logic to deliver real-time insights and AI based feedback for non-expert users. We derive sports insights and providing feedback with minimal computational resources, while showcasing the performance and reliability metrics. In the end, we suggest other future research directions like combining sensors, and AR/VR. This work caters to researchers, engineers, sport scientists, etc., as both technical resource and a valid blueprint to implement a similar or improved real-time HPE analysis system for athletic performance enhancement or other purposes.
Abstract:Applying Human Pose Estimation (HPE) in real world environments remains a challenging task, this paper explores and surveys real time HPE approaches and their limitations in sports analysis for individuals, alongside developing a practical lightweight prototype for real world testing and usage. The older marker-based motion capture systems evolving to the modern accessible and adaptable markerless deep learning approaches, this survey explores the foundational architectures, which balance precision and efficiency. We also compare algorithmic frameworks (top-down, bottom-up, one-stage approaches, etc.) on practical deployment metrics such as inference latency, frame rate, mean per-joint position error, and temporal jitter to guide model selection process for sports application. As our prime contribution, we are proposing a modular, lightweight software prototype, which uses MediaPipe HPE framework with multiple exercise specific logic to deliver real-time insights and AI based feedback for non-expert users. We derive sports insights and providing feedback with minimal computational resources, while showcasing the performance and reliability metrics. In the end, we suggest other future research directions like combining sensors, and AR/VR. This work caters to researchers, engineers, sport scientists, etc., as both technical resource and a valid blueprint to implement a similar or improved real-time HPE analysis system for athletic performance enhancement or other purposes.
Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2606.09842 [cs.HC]
(or arXiv:2606.09842v1 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2606.09842 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 305 words
Related coverage
Performance Profiling on AMD GPUs - Part 4: Fortran OpenMP Offload Edition
AMD · Jun 1, 2026
A Probabilistic Framework for Learnable Optimization Algorithms
arXiv · Aug 17, 2026
Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 1
NVIDIA · Oct 23, 2026
Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations
arXiv · Aug 18, 2026