Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yan, Zhao, Xiong
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.15665
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911601203871744
author Zhang, Yan
Zhao, Xiong
author_facet Zhang, Yan
Zhao, Xiong
contents Markerless 3D movement analysis from monocular video enables accessible biomechanical assessment in clinical and sports settings. However, most research-grade pipelines rely on GPU acceleration, limiting deployment on consumer-grade hardware and in low-resource environments. In this work, we optimize a monocular 3D biomechanics pipeline derived from the MonocularBiomechanics framework for efficient CPU-only execution. Through profiling-driven system optimization, including model initialization restructuring, elimination of disk I/O serialization, and improved CPU parallelization. Experiments on a consumer workstation (AMD Ryzen 7 9700X CPU) show a 2.47x increase in processing throughput and a 59.6\% reduction in total runtime, with initialization latency reduced by 4.6x. Despite these changes, biomechanical outputs remain highly consistent with the baseline implementation (mean joint-angle deviation 0.35$^\circ$, $r=0.998$). These results demonstrate that research-grade vision-based biomechanics pipelines can be deployed on commodity CPU hardware for scalable movement assessment.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15665
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CPU Optimization of a Monocular 3D Biomechanics Pipeline for Low-Resource Deployment
Zhang, Yan
Zhao, Xiong
Computer Vision and Pattern Recognition
Performance
Markerless 3D movement analysis from monocular video enables accessible biomechanical assessment in clinical and sports settings. However, most research-grade pipelines rely on GPU acceleration, limiting deployment on consumer-grade hardware and in low-resource environments. In this work, we optimize a monocular 3D biomechanics pipeline derived from the MonocularBiomechanics framework for efficient CPU-only execution. Through profiling-driven system optimization, including model initialization restructuring, elimination of disk I/O serialization, and improved CPU parallelization. Experiments on a consumer workstation (AMD Ryzen 7 9700X CPU) show a 2.47x increase in processing throughput and a 59.6\% reduction in total runtime, with initialization latency reduced by 4.6x. Despite these changes, biomechanical outputs remain highly consistent with the baseline implementation (mean joint-angle deviation 0.35$^\circ$, $r=0.998$). These results demonstrate that research-grade vision-based biomechanics pipelines can be deployed on commodity CPU hardware for scalable movement assessment.
title CPU Optimization of a Monocular 3D Biomechanics Pipeline for Low-Resource Deployment
topic Computer Vision and Pattern Recognition
Performance
url https://arxiv.org/abs/2604.15665