Mösch Lucas, Barz Isabelle, Müller Anna, Pereira Carina B, Moormann Dieter, Czaplik Michael, Follmann Andreas
Department of Anesthesiology, Faculty of Medicine, RWTH Aachen University, 52074 Aachen, Germany.
Institute of Flight System Dynamics, RWTH Aachen University, 52062 Aachen, Germany.
Bioengineering (Basel). 2023 Mar 7;10(3):336. doi: 10.3390/bioengineering10030336.
The ability to use drones to obtain important vital signs could be very valuable for emergency personnel during mass-casualty incidents. The rapid and robust remote assessment of heart rates could serve as a life-saving decision aid for first-responders. With the flight sensor data of a specialized drone, a pipeline was developed to achieve a robust, non-contact assessment of heart rates through remote photoplethysmography (rPPG). This robust assessment was achieved through adaptive face-aware exposure and comprehensive de-noising of a large number of predicted noise sources. In addition, we performed a proof-of-concept study that involved 18 stationary subjects with clean skin and 36 recordings of their vital signs, using the developed pipeline in outdoor conditions. In this study, we could achieve a single-value heart-rate assessment with an overall root-mean-squared error of 14.3 beats-per-minute, demonstrating the basic feasibility of our approach. However, further research is needed to verify the applicability of our approach in actual disaster situations, where remote photoplethysmography readings could be impacted by other factors, such as blood, dirt, and body positioning.
在大规模伤亡事件中，利用无人机获取重要生命体征的能力对急救人员而言可能非常有价值。对心率进行快速且可靠的远程评估可为急救人员提供救命的决策辅助。借助一款专业无人机的飞行传感器数据，开发了一种流程，通过远程光电容积脉搏波描记法（rPPG）实现对心率的可靠非接触式评估。这种可靠评估是通过自适应面部感知曝光以及对大量预测噪声源进行全面降噪来实现的。此外，我们进行了一项概念验证研究，涉及18名皮肤清洁的静止受试者，并在户外条件下使用所开发的流程对他们的生命体征进行了36次记录。在这项研究中，我们能够实现单值心率评估，总体均方根误差为每分钟14.3次心跳，证明了我们方法的基本可行性。然而，需要进一步研究来验证我们的方法在实际灾难情况下的适用性，在实际灾难情况中，远程光电容积脉搏波描记法读数可能会受到其他因素的影响，如血液、污垢和身体姿势。
