Remote Photoplethysmography Enhancement with Machine Leaning Methods

Driver’s physiological state is highly correlated to the traffic safety. An affordable and convenient way to monitor driver’s physiological state is remote Photoplethysmography (rPPG). Earlier algorithms achieved high accuracy on measuring rPPG signals in stationary case. But in real cases, such as driving, rPPG signals might be corrupted with interference. To obtain higher Signal-to-Noise-Ratio (SNR) rPPG signals, three algorithms are proposed. The PCA spectral subtraction (PCA-SS) considers the spectrum of the environmental noise and utilizes the energy subtraction to reduce the noise. The machine learning methods, convolution autoencoder (CAE) and multi-channel convolution autoencoder (Multi-CAE), are adopted in order to enhance the rPPG signal. The test data we used are 187 videos recorded in stationary case, passenger case, and real driving situation. In driving situation, the Multi-CAE method, in comparison with the original method provided by W. Wang et al. [1] and G. De Haan et al. [2], achieves 33% & 35% reduction in MAE, RMSE respectively, and 11% improvement in success rate [3].

[1]  Sander Stuijk,et al.  Algorithmic Principles of Remote PPG , 2017, IEEE Transactions on Biomedical Engineering.

[2]  Rosalind W. Picard,et al.  Non-contact, automated cardiac pulse measurements using video imaging and blind source separation , 2022 .

[3]  Frédo Durand,et al.  Detecting Pulse from Head Motions in Video , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Winston H. Hsu,et al.  Learning-based heart rate detection from remote photoplethysmography features , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Bing-Fei Wu,et al.  Motion Resistant Image-Photoplethysmography Based on Spectral Peak Tracking Algorithm , 2018, IEEE Access.

[7]  L. O. Svaasand,et al.  Remote plethysmographic imaging using ambient light. , 2008, Optics express.

[8]  Hong Yan,et al.  A Machine Learning Approach to Improve Contactless Heart Rate Monitoring Using a Webcam , 2014, IEEE Journal of Biomedical and Health Informatics.

[9]  D. Haan,et al.  Improved motion robustness of remote-PPG by using the blood volume pulse signature , 2014 .

[10]  Zhuo Chen,et al.  Deep clustering: Discriminative embeddings for segmentation and separation , 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Shiguang Shan,et al.  SynRhythm: Learning a Deep Heart Rate Estimator from General to Specific , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[12]  Daniel McDuff,et al.  DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks , 2018, ECCV.

[13]  Paris Smaragdis,et al.  Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[14]  Sander Stuijk,et al.  Exploiting Spatial Redundancy of Image Sensor for Motion Robust rPPG , 2015, IEEE Transactions on Biomedical Engineering.

[15]  Gerard de Haan,et al.  Robust Pulse Rate From Chrominance-Based rPPG , 2013, IEEE Transactions on Biomedical Engineering.

[16]  Yu-Bin Yang,et al.  Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections , 2016, ArXiv.

[17]  Sander Stuijk,et al.  Color-Distortion Filtering for Remote Photoplethysmography , 2017, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[18]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Sander Stuijk,et al.  Motion Robust Remote-PPG in Infrared , 2015, IEEE Transactions on Biomedical Engineering.