睡眠期间使用散焦摄像头的隐私保护非接触式心肺监测
Privacy Protected Contactless Cardio-respiratory Monitoring using Defocused Cameras during Sleep
AI总结:
本文提出用散焦摄像头从模糊图像中提取心率和呼吸率,通过活体皮肤检测和运动度量排除异常值,在保护睡眠隐私的同时实现心肺监测,心率MAE为4.4 bpm且与参考值强相关。
摘要:
睡眠期间监测心率(HR)和呼吸率(RR)等生命体征对于评估睡眠质量和检测睡眠障碍具有重要意义。近年来,基于摄像头的心率和呼吸率监测在睡眠监测领域日益普及。然而,在睡眠场景中使用视频摄像头时,所有这些方法都面临严重的隐私问题。本文提出使用散焦摄像头从光学模糊图像中测量生命体征,由于在获取的模糊图像中面部难以被识别,该方法可以从根本上消除隐私侵犯。采用一种涉及活体皮肤检测的空间冗余框架,从近红外(NIR)散焦摄像头中提取心率和呼吸率,并设计了一种运动度量指标来排除由身体运动引起的异常值。在基准测试中,心率测量的总体平均绝对误差(MAE)为4.4 bpm,呼吸率测量的总体平均绝对误差为5.9 bpm。与使用聚焦摄像头的测量结果相比,两者质量均有所下降,但心率的退化程度要小得多,即心率测量与参考值具有很强的相关性($R \geq 0.90$)。初步实验表明,使用散焦摄像头在保护隐私的同时进行心肺监测是可行的。对于稳健的呼吸率测量还需要进一步改进,例如通过基于PPG调制的呼吸率提取方法。
英文摘要:
The monitoring of vital signs such as heart rate (HR) and respiratory rate (RR) during sleep is important for the assessment of sleep quality and detection of sleep disorders. Camera-based HR and RR monitoring gained popularity in sleep monitoring in recent years. However, they are all facing with serious privacy issues when using a video camera in the sleeping scenario. In this paper, we propose to use the defocused camera to measure vital signs from optically blurred images, which can fundamentally eliminate the privacy invasion as face is difficult to be identified in obtained blurry images. A spatial-redundant framework involving living-skin detection is used to extract HR and RR from the defocused camera in NIR, and a motion metric is designed to exclude outliers caused by body motions. In the benchmark, the overall Mean Absolute Error (MAE) for HR measurement is 4.4 bpm, for RR measurement is 5.9 bpm. Both have quality drops as compared to the measurement using a focused camera, but the degradation in HR is much less, i.e. HR measurement has strong correlation with the reference ($R \geq 0.90$). Preliminary experiments suggest that it is feasible to use a defocused camera for cardio-respiratory monitoring while protecting the privacy. Further improvement is needed for robust RR measurement, such as by PPG-modulation based RR extraction.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。