Coot optimization based Enhanced Global Pyramid Network for 3D hand pose estimation

IF 6.3 2区物理与天体物理 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Machine Learning Science and Technology Pub Date : 2022-11-02 DOI:10.1088/2632-2153/ac9fa5

Pallavi Malavath, N. Devarakonda

{"title":"Coot optimization based Enhanced Global Pyramid Network for 3D hand pose estimation","authors":"Pallavi Malavath, N. Devarakonda","doi":"10.1088/2632-2153/ac9fa5","DOIUrl":null,"url":null,"abstract":"Due to its importance in various applications that need human-computer interaction (HCI), the field of 3D hand pose estimation (HPE) has recently got a lot of attention. The use of technological developments, such as deep learning networks has accelerated the development of reliable 3D HPE systems. Therefore, in this paper, a 3D HPE based on Enhanced Global Pyramid Network (EGPNet) is proposed. Initially, feature extraction is done by backbone model of DetNetwork with improved EGPNet. The EGPNet is enhanced by the Smish activation function. After the feature extraction, the HPE is performed based on 3D pose correction network. Additionally, to enhance the estimation performance, Coot optimization algorithm is used to optimize the error between estimated and ground truth hand pose. The effectiveness of the proposed method is experimented on Bharatanatyam, yoga, Kathakali and sign language datasets with different networks in terms of area under the curve, median end-point-error (EPE) and mean EPE. The Coot optimization is also compared with existing optimization algorithms.","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":" ","pages":""},"PeriodicalIF":6.3000,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Machine Learning Science and Technology","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1088/2632-2153/ac9fa5","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 1

Abstract

Due to its importance in various applications that need human-computer interaction (HCI), the field of 3D hand pose estimation (HPE) has recently got a lot of attention. The use of technological developments, such as deep learning networks has accelerated the development of reliable 3D HPE systems. Therefore, in this paper, a 3D HPE based on Enhanced Global Pyramid Network (EGPNet) is proposed. Initially, feature extraction is done by backbone model of DetNetwork with improved EGPNet. The EGPNet is enhanced by the Smish activation function. After the feature extraction, the HPE is performed based on 3D pose correction network. Additionally, to enhance the estimation performance, Coot optimization algorithm is used to optimize the error between estimated and ground truth hand pose. The effectiveness of the proposed method is experimented on Bharatanatyam, yoga, Kathakali and sign language datasets with different networks in terms of area under the curve, median end-point-error (EPE) and mean EPE. The Coot optimization is also compared with existing optimization algorithms.

查看原文本刊更多论文

基于Coot优化的增强全局金字塔网络三维手部姿态估计

由于其在需要人机交互（HCI）的各种应用中的重要性，三维手姿态估计（HPE）领域最近受到了很多关注。深度学习网络等技术发展的使用加速了可靠的3D HPE系统的开发。因此，本文提出了一种基于增强型全球金字塔网络（EGPNet）的三维HPE。最初，特征提取是通过DetNetwork的主干模型和改进的EGPNet来完成的。Smish激活功能增强了EGPNet。在特征提取之后，基于三维姿态校正网络进行HPE。此外，为了提高估计性能，使用Coot优化算法来优化估计的手部姿态与真实手部姿态之间的误差。在具有不同网络的Bharatanatyam、yoga、Kathakali和手语数据集上，就曲线下面积、中位终点误差（EPE）和平均EPE对所提出方法的有效性进行了实验。并与现有的优化算法进行了比较。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Machine Learning Science and Technology Computer Science-Artificial Intelligence

CiteScore

9.10

自引率

4.40%

发文量

审稿时长

5 weeks

期刊介绍： Machine Learning Science and Technology is a multidisciplinary open access journal that bridges the application of machine learning across the sciences with advances in machine learning methods and theory as motivated by physical insights. Specifically, articles must fall into one of the following categories: advance the state of machine learning-driven applications in the sciences or make conceptual, methodological or theoretical advances in machine learning with applications to, inspiration from, or motivated by scientific problems.