Human posture estimation and action recognition on fitness behavior and fitness

In daily fitness activities, posture recognition and motion capture are extremely important. This study aims to explore skeleton-based action recognition technology and compare the effects of using only skeleton information and fused image features. We introduce an improved spatiotemporal pyramid gr...

Full description

Saved in:
Bibliographic Details
Main Authors: Ying Zhang, Chenqiong Zhao, Yuan Yao, Chunxiao Wang, Guoliang Cai, Gang Wang
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:Alexandria Engineering Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016824007609
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846167141530730496
author Ying Zhang
Chenqiong Zhao
Yuan Yao
Chunxiao Wang
Guoliang Cai
Gang Wang
author_facet Ying Zhang
Chenqiong Zhao
Yuan Yao
Chunxiao Wang
Guoliang Cai
Gang Wang
author_sort Ying Zhang
collection DOAJ
description In daily fitness activities, posture recognition and motion capture are extremely important. This study aims to explore skeleton-based action recognition technology and compare the effects of using only skeleton information and fused image features. We introduce an improved spatiotemporal pyramid graph convolutional network, which enhances the performance of the model by introducing edge importance scores and multi-level feature representation when dealing with specific action recognition tasks. The proposed model is tested on the UW-IOM and TUM kitchen datasets to verify its applicability in real-world scenarios, the mAP of UW-IOM reached 85.89, achieving the best result and proving the effectiveness of the model. Through experiments, we confirm that in certain cases, the accuracy of skeleton information is the key to improving action recognition performance, while in scenarios where image information is not rich or skeleton information is inaccurate, the fusion of image features can provide performance supplements. In addition, we demonstrate the advantages of our method by comparing with existing methods.
format Article
id doaj-art-c1c9d9e480584cd5bb72f2665dc4fadf
institution Kabale University
issn 1110-0168
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series Alexandria Engineering Journal
spelling doaj-art-c1c9d9e480584cd5bb72f2665dc4fadf2024-11-15T06:11:11ZengElsevierAlexandria Engineering Journal1110-01682024-11-01107434442Human posture estimation and action recognition on fitness behavior and fitnessYing Zhang0Chenqiong Zhao1Yuan Yao2Chunxiao Wang3Guoliang Cai4Gang Wang5School of Sports Human Science, Harbin Institute Of Physical Education, Harbin, 150008, ChinaSchool of Sports Human Science, Harbin Institute Of Physical Education, Harbin, 150008, ChinaSchool of Sports Human Science, Harbin Institute Of Physical Education, Harbin, 150008, ChinaSchool of Sports Human Science, Harbin Institute Of Physical Education, Harbin, 150008, ChinaSchool of Sports Human Science, Harbin Institute Of Physical Education, Harbin, 150008, China; Corresponding author.School of Computing and Data Engineering, NingboTech University, Ningbo, 315100, China; Department of Bioengineering, Imperial College London, London, SW7 2AZ, UKIn daily fitness activities, posture recognition and motion capture are extremely important. This study aims to explore skeleton-based action recognition technology and compare the effects of using only skeleton information and fused image features. We introduce an improved spatiotemporal pyramid graph convolutional network, which enhances the performance of the model by introducing edge importance scores and multi-level feature representation when dealing with specific action recognition tasks. The proposed model is tested on the UW-IOM and TUM kitchen datasets to verify its applicability in real-world scenarios, the mAP of UW-IOM reached 85.89, achieving the best result and proving the effectiveness of the model. Through experiments, we confirm that in certain cases, the accuracy of skeleton information is the key to improving action recognition performance, while in scenarios where image information is not rich or skeleton information is inaccurate, the fusion of image features can provide performance supplements. In addition, we demonstrate the advantages of our method by comparing with existing methods.http://www.sciencedirect.com/science/article/pii/S1110016824007609FitnessGesture recognitionSkeletonMotion captureFusionSmart equipment
spellingShingle Ying Zhang
Chenqiong Zhao
Yuan Yao
Chunxiao Wang
Guoliang Cai
Gang Wang
Human posture estimation and action recognition on fitness behavior and fitness
Alexandria Engineering Journal
Fitness
Gesture recognition
Skeleton
Motion capture
Fusion
Smart equipment
title Human posture estimation and action recognition on fitness behavior and fitness
title_full Human posture estimation and action recognition on fitness behavior and fitness
title_fullStr Human posture estimation and action recognition on fitness behavior and fitness
title_full_unstemmed Human posture estimation and action recognition on fitness behavior and fitness
title_short Human posture estimation and action recognition on fitness behavior and fitness
title_sort human posture estimation and action recognition on fitness behavior and fitness
topic Fitness
Gesture recognition
Skeleton
Motion capture
Fusion
Smart equipment
url http://www.sciencedirect.com/science/article/pii/S1110016824007609
work_keys_str_mv AT yingzhang humanpostureestimationandactionrecognitiononfitnessbehaviorandfitness
AT chenqiongzhao humanpostureestimationandactionrecognitiononfitnessbehaviorandfitness
AT yuanyao humanpostureestimationandactionrecognitiononfitnessbehaviorandfitness
AT chunxiaowang humanpostureestimationandactionrecognitiononfitnessbehaviorandfitness
AT guoliangcai humanpostureestimationandactionrecognitiononfitnessbehaviorandfitness
AT gangwang humanpostureestimationandactionrecognitiononfitnessbehaviorandfitness