马 琳,刘春阳,谢赛宝,班宇煊,隋 新,黄 艳,杨晓康.基于人像识别和感兴趣区域定位的
红外图像测温研究[J].电子测量与仪器学报,2023,37(2):186-192 |
基于人像识别和感兴趣区域定位的
红外图像测温研究 |
Research on infrared image temperature measurement based onportrait recognition and region of interest localization |
|
DOI: |
中文关键词: 红外测温 深度学习 人像识别 YOLO 算法 精准测温 |
英文关键词:infrared temperature measurement deep learning portrait recognition YOLO algorithm accurate temperature measurement |
基金项目:国家自然科学基金(52105574)、河南省重点研发与推广专项(科技攻关)项目(222102220079) 、河南省高等学校青年骨干教师培养计划(2019GGJS082)、河南省高等学校重点科研项目基础研究计划项目(17A460003)资助 |
|
Author | Institution |
Ma Lin | 1. School of Mechatronics Engineering, Henan University of Science and Technology |
Liu Chunyang | 1. School of Mechatronics Engineering, Henan University of Science and Technology, 2. Henan Province Key Laboratory of Mechanical Design and Transmission System,3. Longmen Laboratory |
Xie Saibao | 1. School of Mechatronics Engineering, Henan University of Science and Technology |
Ban Yuxuan | 1. School of Mechatronics Engineering, Henan University of Science and Technology |
Sui Xin | 1. School of Mechatronics Engineering, Henan University of Science and Technology, 2. Henan Province Key Laboratory of Mechanical Design and Transmission System |
Huang Yan | 1. School of Mechatronics Engineering, Henan University of Science and Technology |
Yang Xiaokang | 1. School of Mechatronics Engineering, Henan University of Science and Technology |
|
摘要点击次数: 409 |
全文下载次数: 854 |
中文摘要: |
非接触式温度测量是应对“新冠”、流感等传播性疫情进行大流量防疫筛查的有效手段,可以避免交叉感染的风险,能
够实现公共场合的人体体温监测。 本文基于 YOLOv5 和红外相机设计了人像识别及测温系统,使用红外图像进行人脸目标检
测,提出了一套依靠人脸及遮挡物的额头区域辅助定位算法。 针对人像以及有眼镜、口罩、帽子等遮挡情况构建了数据集,对红
外图像的人像识别进行了训练和预测,实现了针对面部感兴趣区域(额头)的精准定位,并通过该定位实现人体测温,采用 C#开
发了软件界面,实现了对红外图像及其温度的可视化显示与管理。 经过实验测试,基于 YOLOv5 的预测平均准确率为 94%,额
头区域的辅助定位精度达到 97. 3%,算法对红外测温效果的影响在±0. 15℃以内。 系统可长期运行,且对多应用场景具有较好
的适用性。 |
英文摘要: |
Contactless temperature measurement is an effective means to conduct mass epidemic prevention screening in response to the
“COVID-19”, influenza and other infectious diseases, could avoid the risk of cross infection and realize human body temperature
monitoring in public places, and can realize human body temperature monitoring in public places. In this paper, a portrait recognition
and temperature measurement system are designed based on YOLOv5 and infrared camera. Infrared images are used for face target
detection, and a set of forehead region assisted location algorithm relying on face and occluding objects is proposed. For portrait and
glasses, masks, hats and other condition to construct the data set, as recognition of infrared image training and forecasting, implements
for facial interested area (forehead) precise positioning and temperature measurement, and realize human body temperature measurement
by this location, using C # development of the software interface, realize the visualization display and management of infrared image and
its temperature. After the experimental test, the average accuracy of the prediction based on YOLOv5 is 94%, and the auxiliary
positioning accuracy of the forehead region reaches 97. 3%. The influence of the algorithm on the infrared temperature measurement
effect is within ±0. 15℃ . The system can run for a long time and has good applicability to multiple application scenarios. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|