基于VMD的无人机视频呼吸率检测  

Video Respiration Rate Detection for UAV Based on VMD

作　　者：张礼俊 陈鲸 杨学志 沈晶[4,5] 吴克伟 ZHANG Li-Jun;CHEN Jing;YANG Xue-Zhi;SHEN Jing;WU Ke-Wei(School of Computer and Information,Hefei University of Technology,Hefei 230009,China;Key Laboratory of Industrial Safety and Emergency Technology of Anhui Province,Hefei 230009,China;School of Software,Hefei University of Technology,Hefei 230009,China;School of Electronics and Electrical Engineering,Hefei Normal University,Hefei 230061,China;Key Laboratory of Electronic Information System Simulation Design of Anhui Province,Hefei 230061,China)

机构地区：[1]合肥工业大学计算机与信息学院,合肥230009 [2]工业安全与应急技术安徽省重点实验室,合肥230009 [3]合肥工业大学软件学院,合肥230009 [4]合肥师范学院电子与电气工程学院,合肥230061 [5]电子信息系统仿真设计安徽省重点实验室,合肥230061

出　　处：《计算机系统应用》2021年第8期142-149,共8页Computer Systems & Applications

基　　金：国防科技创新特区项目(1816321TS00106101);工业安全与应急技术安徽省重点实验室2019自主创新专项(PA2019GDPK0070);工业安全与应急技术安徽省重点实验室2020年度自主创新专项(PA2020GDSK0079)。

摘　　要：无人机晃动是视觉传感器提取生命体征造成误差的重要原因.针对该问题,本文提出一种基于变分模态分解(VMD)的抗无人机晃动呼吸率检测方法.首先,采用复可控金字塔提取呼吸率的初始特征,其次,设计一种基于变分模态分解的呼吸信号提取方法,获得候选的呼吸模态信号,最后,选择方差最小的本征模态实现呼吸率检测.本文实验结果表明,在无人机自身正常晃动情况下,本文方法能够有效提取本征呼吸信号.本文方法能在不同受测距离情况下实现不同人体姿态下的呼吸率检测,其检测精度优于现有方法.The shaking of Unmanned Aerial Vehicles(UAVs)is an important reason for the error caused by the visual sensors in extracting vital signs.To solve this problem,this paper proposes a method of respiration rate detection based on Variational Mode Decomposition(VMD),which is immune to UAV shaking.First,a complex controllable pyramid is used to extract the initial characteristics of respiration rates.Second,an extraction method of respiratory signals based on VMD is designed to obtain the candidate respiratory modal signals.Third,the eigenmodes with the minimum variance are selected for respiration rate detection.The experimental results show that the proposed method can effectively extract the intrinsic respiratory signals under the normal shaking condition of the UAVs.Moreover,this method can detect respiration rates in different human postures at different measured distances,and its detection accuracy is higher than that of the existing methods.

关 键 词：呼吸率 灾后搜救 无人机 视频 变分模态分解 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] V19[自动化与计算机技术—计算机科学与技术]