版权说明 操作指南
首页 > 成果 > 详情

Infrared head pose estimation with multi-scales feature fusion on the IRHP database for human attention recognition

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;Wang, Xiang;Zhang, Wei*;Zhang, Zhaoli;Li, You-Fu
通讯作者:
Zhang, Wei
作者机构:
[Wang, Xiang; Zhang, Zhaoli; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
[Wang, Xiang; Zhang, Wei] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.
[Li, You-Fu; Liu, Hai] City Univ Hong Kong, Dept Mech Engn, Hong Kong, Peoples R China.
通讯机构:
[Zhang, Wei] C
Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.
语种:
英文
关键词:
Attention recognition;Convolutional neural network;Feature fusion;Head pose estimation;Infrared image
期刊:
Neurocomputing
ISSN:
0925-2312
年:
2020
卷:
411
页码:
510-520
基金类别:
National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61875068, 61873220, 61977031, 61505064]; National Key Research and Development Program of China [2018YFB1004505]; Research Grants Council of Hong KongHong Kong Research Grants Council [CityU 11205015, CityU 11255716]; Fundamental Research Funds for the Central UniversitiesFundamental Research Funds for the Central Universities [CCNU20ZT017, CCNU2020ZN008]
机构署名:
本校为第一且通讯机构
院系归属:
国家数字化学习工程技术研究中心
摘要:
Head pose estimation (HPE) has been widely applied in human attention recognition, robot vision and assistant driving. Infrared (IR) images bear unique advantages of being still effective under visible scenarios, which are resistance to illumination changing and strong penetration. However, the lack of public IR database hinders the research progress in the low illumination environment. In this paper, we establish a first-of-its-kind infrared head pose (IRHP) database and propose a novel convolutional neural network architecture IRHP-Net on the IRHP database. The IRHP database contains 145 kin...

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