A novel approach for yoga pose estimation based on in-depth analysis of human body joint detection accuracy

Author:

Desai Miral1,Mewada Hiren2

Affiliation:

1. Department of EC Engineering, CSPIT, CHARUSAT, Anand, India

2. Electrical Engineering Department, Prince Mohammad Bin Fahd University, AL Khobar, Saudi Arabia

Abstract

Virtual motion and pose from images and video can be estimated by detecting body joints and their interconnection. The human body has diverse and complicated poses in yoga, making its classification challenging. This study estimates yoga poses from the images using a neural network. Five different yoga poses, viz. downdog, tree, plank, warrior2, and goddess in the form of RGB images are used as the target inputs. The BlazePose model was used to localize the body joints of the yoga poses. It detected a maximum of 33 body joints, referred to as keypoints, covering almost all the body parts. Keypoints achieved from the model are considered as predicted joint locations. True keypoints, as the ground truth body joint for individual yoga poses, are identified manually using the open source image annotation tool named Makesense AI. A detailed analysis of the body joint detection accuracy is proposed in the form of percentage of corrected keypoints (PCK) and percentage of detected joints (PDJ) for individual body parts and individual body joints, respectively. An algorithm is designed to measure PCK and PDJ in which the distance between the predicted joint location and true joint location is calculated. The experiment evaluation suggests that the adopted model obtained 93.9% PCK for the goddess pose. The maximum PCK achieved for the goddess pose, i.e., 93.9%, PDJ evaluation was carried out in the staggering mode where maximum PDJ is obtained as 90% to 100% for almost all the body joints.

Publisher

PeerJ

Subject

General Computer Science

Reference30 articles.

1. BlazePose: on-device real-time body pose tracking;Bazarevsky,2020

2. Blazeface: sub-millisecond neural face detection on mobile GPUs;Bazarevsky,2019

3. OpenPose: real-time multi person 2D pose estimation using Part Affinity Fields;Cao,2018

4. Human pose estimation with iterative error feedback;Carreira,2016

5. Adversarial posenet: a structure-aware convolutional network for human pose estimation;Chen,2017

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Advanced Yoga Pose Estimation: Enhancing PoseNet with Adaptive Key Point Elimination;2024 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI);2024-04-17

2. Exploration of deep learning architectures for real-time yoga pose recognition;Multimedia Tools and Applications;2024-03-08

3. Application of deep learning and feature selection technique on external root resorption identification on CBCT images;BMC Oral Health;2024-02-19

4. Convolutional Neural Network Algorithm for Yoga Pose Estimation System as an Exercise Assistant;2023 11th International Conference on Cyber and IT Service Management (CITSM);2023-11-10

5. A Novel Approach for Developing Inclusive Real-Time Yoga Pose Detection for Health and Wellness Using Raspberry pi;2023 7th International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS);2023-11-02

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3