Enhancing accuracy in dynamic pose estimation for sports competitions using HRPose: A hybrid approach integrating SinglePose AI

Human pose estimation plays a critical role in various applications, such as sports performance evaluation, rehabilitation, and human–computer interaction. Recent advancements in deep learning have significantly improved the accuracy and robustness of human pose estimation models. However, challenge...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Han, Mingnong Yi, Wei Feng, Feng Qi, Yining Zhou
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Alexandria Engineering Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016825005587
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849229304292966400
author Rui Han
Mingnong Yi
Wei Feng
Feng Qi
Yining Zhou
author_facet Rui Han
Mingnong Yi
Wei Feng
Feng Qi
Yining Zhou
author_sort Rui Han
collection DOAJ
description Human pose estimation plays a critical role in various applications, such as sports performance evaluation, rehabilitation, and human–computer interaction. Recent advancements in deep learning have significantly improved the accuracy and robustness of human pose estimation models. However, challenges remain in dynamic environments, especially in sports competitions, where high-speed movements, occlusions, and complex backgrounds often hinder accurate estimation. This paper proposes HRPose, a novel approach that combines HRNet for feature extraction and SinglePose AI for precise keypoint localization. It maintains high-resolution feature maps throughout the feature extraction process, enabling the model to capture fine-grained spatial details. SinglePose AI uses these features to generate and refine keypoint heatmaps, achieving accurate pose estimation even in challenging conditions. We evaluate HRPose on benchmark datasets, including the MPII Human Pose and PoseTrack datasets, and compare it with several models. Our results demonstrate that HRPose achieves superior performance in terms of mAP, precision, and robustness. Additionally, we discuss the real-time performance of HRPose and its potential applications in various domains, such as sports, healthcare, and rehabilitation. Future work will focus on improving the model’s robustness to extreme conditions, such as low lighting and motion blur, and exploring its integration with multimodal data for more comprehensive analysis.
format Article
id doaj-art-533ac7e2fe9a4d6a9ceccb6a0a8f9370
institution Kabale University
issn 1110-0168
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Alexandria Engineering Journal
spelling doaj-art-533ac7e2fe9a4d6a9ceccb6a0a8f93702025-08-22T04:55:14ZengElsevierAlexandria Engineering Journal1110-01682025-08-0112720021310.1016/j.aej.2025.04.062Enhancing accuracy in dynamic pose estimation for sports competitions using HRPose: A hybrid approach integrating SinglePose AIRui Han0Mingnong Yi1Wei Feng2Feng Qi3Yining Zhou4Key Laboratory of Sports Engineering of General Administration of Sport of China, Wuhan Sports University, 430079, Wuhan, Hubei, ChinaKey Laboratory of Sports Engineering of General Administration of Sport of China, Wuhan Sports University, 430079, Wuhan, Hubei, China; Corresponding author.School of Artificial Intelligence and Automation Huazhong University of Science and Technology(HUST), 430074, Wuhan, Hubei, ChinaEngineering Research Center of Sports Health Intelligent Equipment of Hubei Province, Wuhan Sports University, 430079, Wuhan, Hubei, China; Research Center of Sports Equipment Engineering Technology of Hubei Province, Wuhan Sports University, 430079, Wuhan, Hubei, ChinaTexas A&M University Newark, CA, United States of AmericaHuman pose estimation plays a critical role in various applications, such as sports performance evaluation, rehabilitation, and human–computer interaction. Recent advancements in deep learning have significantly improved the accuracy and robustness of human pose estimation models. However, challenges remain in dynamic environments, especially in sports competitions, where high-speed movements, occlusions, and complex backgrounds often hinder accurate estimation. This paper proposes HRPose, a novel approach that combines HRNet for feature extraction and SinglePose AI for precise keypoint localization. It maintains high-resolution feature maps throughout the feature extraction process, enabling the model to capture fine-grained spatial details. SinglePose AI uses these features to generate and refine keypoint heatmaps, achieving accurate pose estimation even in challenging conditions. We evaluate HRPose on benchmark datasets, including the MPII Human Pose and PoseTrack datasets, and compare it with several models. Our results demonstrate that HRPose achieves superior performance in terms of mAP, precision, and robustness. Additionally, we discuss the real-time performance of HRPose and its potential applications in various domains, such as sports, healthcare, and rehabilitation. Future work will focus on improving the model’s robustness to extreme conditions, such as low lighting and motion blur, and exploring its integration with multimodal data for more comprehensive analysis.http://www.sciencedirect.com/science/article/pii/S1110016825005587Human pose estimationSports analysisReal-time processingKeypoint localizationDeep learningSinglePose AI
spellingShingle Rui Han
Mingnong Yi
Wei Feng
Feng Qi
Yining Zhou
Enhancing accuracy in dynamic pose estimation for sports competitions using HRPose: A hybrid approach integrating SinglePose AI
Alexandria Engineering Journal
Human pose estimation
Sports analysis
Real-time processing
Keypoint localization
Deep learning
SinglePose AI
title Enhancing accuracy in dynamic pose estimation for sports competitions using HRPose: A hybrid approach integrating SinglePose AI
title_full Enhancing accuracy in dynamic pose estimation for sports competitions using HRPose: A hybrid approach integrating SinglePose AI
title_fullStr Enhancing accuracy in dynamic pose estimation for sports competitions using HRPose: A hybrid approach integrating SinglePose AI
title_full_unstemmed Enhancing accuracy in dynamic pose estimation for sports competitions using HRPose: A hybrid approach integrating SinglePose AI
title_short Enhancing accuracy in dynamic pose estimation for sports competitions using HRPose: A hybrid approach integrating SinglePose AI
title_sort enhancing accuracy in dynamic pose estimation for sports competitions using hrpose a hybrid approach integrating singlepose ai
topic Human pose estimation
Sports analysis
Real-time processing
Keypoint localization
Deep learning
SinglePose AI
url http://www.sciencedirect.com/science/article/pii/S1110016825005587
work_keys_str_mv AT ruihan enhancingaccuracyindynamicposeestimationforsportscompetitionsusinghrposeahybridapproachintegratingsingleposeai
AT mingnongyi enhancingaccuracyindynamicposeestimationforsportscompetitionsusinghrposeahybridapproachintegratingsingleposeai
AT weifeng enhancingaccuracyindynamicposeestimationforsportscompetitionsusinghrposeahybridapproachintegratingsingleposeai
AT fengqi enhancingaccuracyindynamicposeestimationforsportscompetitionsusinghrposeahybridapproachintegratingsingleposeai
AT yiningzhou enhancingaccuracyindynamicposeestimationforsportscompetitionsusinghrposeahybridapproachintegratingsingleposeai