基于深度图像的非接触呼吸频率检测方法  

Non-contact respiratory frequency detection method based on depth image

作　　者：黄旭龙 刘治宏 梅宇博 杨晓梅[1] HUANG Xu-long;LIU Zhi-hong;MEI Yu-bo;YANG Xiao-mei(College of Electrical Engineering,Sichuan University,Chengdu 610065,China;College of Artificial Intelligence,Xi’an Jiaotong University,Xi’an 710049,China)

机构地区：[1]四川大学电气工程学院,四川成都610065 [2]西安交通大学人工智能学院,陕西西安710049

出　　处：《计算机工程与设计》2023年第4期1151-1158,共8页Computer Engineering and Design

基　　金：四川省科技计划基金项目(重点研发项目)(2020YFS0085)。

摘　　要：为便捷且有效地实现对人体呼吸频率的日常检测,提出基于深度图像的非接触式呼吸频率检测方法。利用Real-Sense相机获取的人体及背景的深度图像信息,根据提出的最大距离限制法与最大外轮廓提取算法分别消除空洞噪声和近距离干扰物体的影响,凸出人体深度图像;通过Zhang-Suen细化算法提取人体骨架,结合骨架关节信息实现对胸腔呼吸区域的定位;利用主成分分析算法(PCA)提取胸腔区域深度图像包含的呼吸信号数据,进一步通过峰值检测法求解人体呼吸频率。实验结果表明,该方法可有效实现对人体呼吸频率的非接触式检测,具有良好的准确性。To realize the daily detection of human respiratory frequency effectively and conveniently,a non-contact respiratory frequency detection method based on depth image information obtained by RealSense camera was proposed.The proposed maximum distance limit method and the maximum external contour extraction algorithm were used to eliminate the influence of cavity noise and close-range interference objects respectively,and the depth image of human body was obtained.The human skeleton was extracted using Zhang-Suen refinement algorithm,and the location of the thoracic breathing area was realized by combining the skeleton joint information.The principal component analysis algorithm(PCA)was used to extract the respiratory signal data contained in the depth image of the chest area,and the human respiratory frequency was further solved using the peak detection method.Experimental results show that the proposed method can effectively non-contactually realize the detection of human respiratory frequency with high accuracy.

关 键 词：深度图像 非接触式 呼吸频率检测 最大距离限制 最大外轮廓提取 Zhang-Suen细化 主成分分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]