版权说明 操作指南
首页 > 成果 > 详情

Human pose recognition via adaptive distribution encoding for action perception in the self-regulated learning process

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Liu, Hai;Chen, Yu;Zhao, Wanli;Zhang, Shengqiang;Zhang, Zhaoli
通讯作者:
Zhaoli Zhang
作者机构:
[Zhao, Wanli; Zhang, Shengqiang; Zhang, Zhaoli; Chen, Yu; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, 152 Luoyu Rd, Wuhan, Hubei, Peoples R China.
[Liu, Hai] UCL, UCL Interact Ctr, London, England.
通讯机构:
[Zhaoli Zhang] N
National Engineering Research Center for E-Learning, Central China Normal University, 152 Luoyu Road, Wuhan, Hubei, China
语种:
英文
关键词:
Gaussian coordinate encoding;Human pose recognition;Infrared imaging;K-12 education;Self-regulated learning
期刊:
Infrared Physics & Technology
ISSN:
1350-4495
年:
2021
卷:
114
页码:
103660
基金类别:
The developed EDE model includes three modules, such as feature extraction module, heatmap generation module and decoding module. In Fig. 2, we show the overall model architecture of the proposed network. Given an input IR image, we first preprocess it, which includes encoding different parts, and at highly hinged parts, we judge whether to generate it according to the angle. The elliptical Gaussian label, the encoded heatmap will be sent to the network. In this article, we choose the RLNet as
机构署名:
本校为第一机构
院系归属:
国家数字化学习工程技术研究中心
摘要:
Human pose recognition (HPR) under infrared imaging is considered a significant role for action perception in the self-regulated learning process. In this article, we propose a novel elliptical distribution encoding (EDE) method for understanding the human behavior through body poses under infrared imaging. Firstly, to reveal the relationship between the adjacent joint points, the elliptical Gaussian coordinate coding is proposed for the human skeleton direction description. Then, the KL divergence is introduced to measure the different between...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com