ASHN for Multi-Human Pose Estimation

Pan Gao, Zhuhua Hu
{"title":"ASHN for Multi-Human Pose Estimation","authors":"Pan Gao, Zhuhua Hu","doi":"10.1109/ACAIT56212.2022.10137930","DOIUrl":null,"url":null,"abstract":"Due to the diversity of human body posture, there are problems such as occlusion of key points, difference of target scale and background blur among people. Therefore, multi-human pose estimation is still a challenging task. The existing deep learning-based multi-body pose estimation methods are mainly divided into top-down and bottom-up, but most of them do not make full use of local features in the network. In this paper, convolutional block attention module(CBAM) and Focal L2 Loss were used to process the context information of convolutional neural network and consolidate local features. Specifically, we propose attention-containing stacked hourglass network (ASHN). ASHN is based on a stacked hourglass network, with the addition of a convolutional block attention module (CBAM) module to improve performance, combined with Focal L2 Loss in the model. Compared with the existing methods, our method achieves competitive performance, achieving 66.8% AP, 72.1% AP75 and 65.4% APM on COCO data sets.","PeriodicalId":398228,"journal":{"name":"2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ACAIT56212.2022.10137930","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

Due to the diversity of human body posture, there are problems such as occlusion of key points, difference of target scale and background blur among people. Therefore, multi-human pose estimation is still a challenging task. The existing deep learning-based multi-body pose estimation methods are mainly divided into top-down and bottom-up, but most of them do not make full use of local features in the network. In this paper, convolutional block attention module(CBAM) and Focal L2 Loss were used to process the context information of convolutional neural network and consolidate local features. Specifically, we propose attention-containing stacked hourglass network (ASHN). ASHN is based on a stacked hourglass network, with the addition of a convolutional block attention module (CBAM) module to improve performance, combined with Focal L2 Loss in the model. Compared with the existing methods, our method achieves competitive performance, achieving 66.8% AP, 72.1% AP75 and 65.4% APM on COCO data sets.
多人体姿态估计的ASHN算法
由于人体姿态的多样性,人与人之间存在关键点遮挡、目标尺度差异、背景模糊等问题。因此,多人体姿态估计仍然是一项具有挑战性的任务。现有的基于深度学习的多体姿态估计方法主要分为自顶向下和自底向上两种,但大多数方法都没有充分利用网络中的局部特征。本文采用卷积块注意模块(convolutional block attention module, CBAM)和Focal L2 Loss对卷积神经网络的上下文信息进行处理,巩固局部特征。具体来说,我们提出了包含注意力的堆叠沙漏网络(ASHN)。ASHN基于堆叠沙漏网络,增加了卷积块注意模块(CBAM)模块以提高性能,并结合了模型中的Focal L2 Loss。与现有方法相比,我们的方法在COCO数据集上实现了66.8%的AP、72.1%的AP75和65.4%的APM,具有较强的竞争力。
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:481959085
Book学术官方微信