李俊杰1,
贾勇1
1.成都理工大学信息科学与技术学院(网络安全学院、牛津布鲁克斯学院) 成都 610059
2.工业物联网与网络化控制教育部重点实验室 重庆 400065
3.太赫兹科学技术四川省重点实验室 成都 610054
基金项目:国家自然科学基金(61771096)，工业物联网与网络化控制教育部重点实验室开放基金(2020FF06)，太赫兹科学技术四川省重点实验室开放基金(THZSC202001)
详细信息
作者简介:易诗：男，1983年生，高级实验师，研究方向为深度学习红外图像处理
李俊杰：男，1997年生，硕士生，研究方向为深度学习图像处理
贾勇：男，1986年生，副教授，研究方向为穿墙雷达图像处理
通讯作者:易诗 549745481@qq.com
中图分类号:TN911.73; TP391计量
文章访问数:93
HTML全文浏览量:88
PDF下载量:36
被引次数:0
出版历程
收稿日期:2020-10-09
修回日期:2021-04-22
网络出版日期:2021-07-15
刊出日期:2021-12-21
Instance Segmentation of Thermal Imaging Temperature Measurement Region Based on Infrared Attention Enhancement Mechanism
Shi YI1, 2, 3,,,Junjie LI1,
Yong JIA1
1. College of Information Science and Technology(College of Cyber Security, College of Oxford Brookes), Chengdu University of Technology, Chengdu 610059, China
2. Key Laboratory of Industrial Internet of Things & Networked Control, Ministry of Education, Chongqing 400065, China
3. Terahertz Science and Technology Key Laboratory of Sichuan Province, Chengdu 610054, China
Funds:The National Natural Science Foundation of China (61771096), The Key Laboratory of Industrial Internet of Things & Networked Control Foundation, Ministry of Education (2020FF06), The Terahertz Science and Technology Key Laboratory Foundation of Sichuan Province (THZSC202001)
摘要
摘要:AI+热成像人体温度监测系统被广泛用于人群密集的人体实时温度测量。此类系统检测人的头部区域进行温度测量，由于各类遮挡，温度测量区域可能太小而无法正确测量。为了解决这个问题，该文提出一种融合红外注意力提升机制的无锚点实例分割网络，用于实时红外热成像温度测量区域实例分割。该文所提出的实例分割网络在检测阶段和分割阶段融合红外空间注意力模块(ISAM)，旨在准确分割红外图像中的头部裸露区域，以进行准确实时的温度测量。结合公共热成像面部数据集和采集的红外热成像数据集，制作了“热成像温度测量区域分割数据集”用于网络训练。实验结果表明：该方法对红外热成像图像中头部裸露测温区域的平均检测精度达到88.6%，平均分割精度达到86.5%，平均处理速度达到33.5 fps，在评价指标上优于大多数先进的实例分割方法。
关键词:红外热成像/
人体体温监测系统/
红外注意力提升机制/
无锚点实例分割网络/
热成像温度测量区域分割数据集
Abstract:AI+thermal imaging human body temperature monitoring system is widely used for real-time temperature measurement of human body in dense crowds. The artificial intelligence method used in such systems detects the human head region for temperature measurement. The temperature measurement area may be too small to measure correctly due to occlusion. To tackle this problem, an anchor-free instance segmentation network incorporating infrared attention enhancement mechanism is proposed for real-time infrared thermal imaging temperature measurement area segmentation. The instance segmentation network proposed in this paper integrates the Infrared Spatial Attention Module (ISAM) in the detection stage and the segmentation stage, aiming to accurately segment the bare head area in the infrared image. Combined with the public thermal imaging facial dataset and the collected infrared thermal imaging dataset, the "thermal imaging temperature measurement area segmentation dataset" is produced. Experimental results demonstrate that this method reached an average detection precision of 88.6%, average mask precision of 86.5%, average processing speed of 33.5 fps. This network is superior to most state of the art instance segmentation methods in objective evaluation metrics.
Key words:Infrared thermal imaging/
Human body temperature monitoring system/
Infrared attention enhancement mechanism/
Anchor-free instance segmentation network/
Thermal imaging temperature measurement area segmentation dataset
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=1766225d-bada-44d7-80f4-dbb91930c3cd
