Enhancing 3D Pose Estimation Accuracy from Multiple Camera Perspectives through Machine Learning Model Integration

Ervinas Gisleris, A. Serackis
{"title":"Enhancing 3D Pose Estimation Accuracy from Multiple Camera Perspectives through Machine Learning Model Integration","authors":"Ervinas Gisleris, A. Serackis","doi":"10.1109/AIEEE58915.2023.10134772","DOIUrl":null,"url":null,"abstract":"In this investigation, we propose a machine learning approach to integrate estimations from two orthogonal camera views, separated by approximately 90 degrees, using a three-layer feed-forward neural network to refine and unify 3D pose estimations. The primary objective is to minimize the discrepancies between the estimated joint coordinates and the ground truth, consequently improving the overall accuracy of the 3D pose estimation process. Our neural network architecture comprises two hidden layers with the ReLU activation function and an output layer with the linear activation function to generate the final 3D coordinates of human skeleton joints. Integration of estimations from two orthogonal camera perspectives allows the model to account for occlusions, varying lighting conditions, and pose diversity, providing a more comprehensive representation of the 3D pose. The network is trained and evaluated on a public CMU Panoptic dataset that contains videos with a wide range of poses.","PeriodicalId":149255,"journal":{"name":"2023 IEEE 10th Jubilee Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE 10th Jubilee Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AIEEE58915.2023.10134772","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

In this investigation, we propose a machine learning approach to integrate estimations from two orthogonal camera views, separated by approximately 90 degrees, using a three-layer feed-forward neural network to refine and unify 3D pose estimations. The primary objective is to minimize the discrepancies between the estimated joint coordinates and the ground truth, consequently improving the overall accuracy of the 3D pose estimation process. Our neural network architecture comprises two hidden layers with the ReLU activation function and an output layer with the linear activation function to generate the final 3D coordinates of human skeleton joints. Integration of estimations from two orthogonal camera perspectives allows the model to account for occlusions, varying lighting conditions, and pose diversity, providing a more comprehensive representation of the 3D pose. The network is trained and evaluated on a public CMU Panoptic dataset that contains videos with a wide range of poses.
通过机器学习模型集成从多个相机角度增强3D姿态估计精度
在这项研究中,我们提出了一种机器学习方法,使用三层前馈神经网络来改进和统一3D姿态估计,以整合两个相距约90度的正交相机视图的估计。主要目标是尽量减少估计的关节坐标与地面真实值之间的差异,从而提高3D姿态估计过程的整体精度。我们的神经网络架构包括两个具有ReLU激活函数的隐藏层和一个具有线性激活函数的输出层,用于生成人体骨骼关节的最终三维坐标。从两个正交的摄像机角度估计的集成允许模型考虑遮挡,不同的照明条件和姿态多样性,提供更全面的3D姿态表示。该网络在公共CMU Panoptic数据集上进行训练和评估,该数据集包含各种姿势的视频。
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信