Video-Based Pulse Rate Variability Measurement Using Periodic Variance Maximization and Adaptive Two-Window Peak Detection
Many previous studies have shown that the remote photoplethysmography (rPPG) can measure the Heart Rate (HR) signal with very high accuracy. The remote measurement of the Pulse Rate Variability (PRV) signal is also possible, but this is much more complicated because it is then necessary to detect th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/10/2752 |
| _version_ | 1797568213457829888 |
|---|---|
| author | Peixi Li Yannick Benezeth Richard Macwan Keisuke Nakamura Randy Gomez Chao Li Fan Yang |
| author_facet | Peixi Li Yannick Benezeth Richard Macwan Keisuke Nakamura Randy Gomez Chao Li Fan Yang |
| author_sort | Peixi Li |
| collection | DOAJ |
| description | Many previous studies have shown that the remote photoplethysmography (rPPG) can measure the Heart Rate (HR) signal with very high accuracy. The remote measurement of the Pulse Rate Variability (PRV) signal is also possible, but this is much more complicated because it is then necessary to detect the peaks on the temporal rPPG signal, which is usually quite noisy and has a lower temporal resolution than PPG signals obtained by contact equipment. Since the PRV signal is vital for various applications such as remote recognition of stress and emotion, the improvement of PRV measurement by rPPG is a critical task. Contact based PRV measurement has already been investigated, but the research on remotely measured PRV is very limited. In this paper, we propose to use the Periodic Variance Maximization (PVM) method to extract the rPPG signal and event-related Two-Window algorithm to improve the peak detection for PRV measurement. We have made several contributions. Firstly, we show that the newly proposed PVM method and Two-Window algorithm can be used for PRV measurement in the non-contact scenario. Secondly, we propose a method to adaptively determine the parameters of the Two-Window method. Thirdly, we compare the algorithm with other attempts for improving the non-contact PRV measurement such as the Slope Sum Function (SSF) method and the Local Maximum method. We calculated several features and compared the accuracy based on the ground truth provided by contact equipment. Our experiments showed that this algorithm performed the best of all the algorithms. |
| first_indexed | 2024-03-10T19:53:15Z |
| format | Article |
| id | doaj.art-199a562f93074313a6bf877d8b4fbfe6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T19:53:15Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-199a562f93074313a6bf877d8b4fbfe62023-11-20T00:09:16ZengMDPI AGSensors1424-82202020-05-012010275210.3390/s20102752Video-Based Pulse Rate Variability Measurement Using Periodic Variance Maximization and Adaptive Two-Window Peak DetectionPeixi Li0Yannick Benezeth1Richard Macwan2Keisuke Nakamura3Randy Gomez4Chao Li5Fan Yang6ImViA-EA7535, Univ. Bourgogne Franche-Comté, 21000 Dijon, FranceImViA-EA7535, Univ. Bourgogne Franche-Comté, 21000 Dijon, FranceLPL, CNRS-UMR7538, Univ. Paris 13, 93430 Villetaneuse, FranceHonda Research Institute Japan Co., Ltd., 8-1 Honcho, Wako-shi, Saitama 351-0114, JapanHonda Research Institute Japan Co., Ltd., 8-1 Honcho, Wako-shi, Saitama 351-0114, JapanState Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaImViA-EA7535, Univ. Bourgogne Franche-Comté, 21000 Dijon, FranceMany previous studies have shown that the remote photoplethysmography (rPPG) can measure the Heart Rate (HR) signal with very high accuracy. The remote measurement of the Pulse Rate Variability (PRV) signal is also possible, but this is much more complicated because it is then necessary to detect the peaks on the temporal rPPG signal, which is usually quite noisy and has a lower temporal resolution than PPG signals obtained by contact equipment. Since the PRV signal is vital for various applications such as remote recognition of stress and emotion, the improvement of PRV measurement by rPPG is a critical task. Contact based PRV measurement has already been investigated, but the research on remotely measured PRV is very limited. In this paper, we propose to use the Periodic Variance Maximization (PVM) method to extract the rPPG signal and event-related Two-Window algorithm to improve the peak detection for PRV measurement. We have made several contributions. Firstly, we show that the newly proposed PVM method and Two-Window algorithm can be used for PRV measurement in the non-contact scenario. Secondly, we propose a method to adaptively determine the parameters of the Two-Window method. Thirdly, we compare the algorithm with other attempts for improving the non-contact PRV measurement such as the Slope Sum Function (SSF) method and the Local Maximum method. We calculated several features and compared the accuracy based on the ground truth provided by contact equipment. Our experiments showed that this algorithm performed the best of all the algorithms.https://www.mdpi.com/1424-8220/20/10/2752remote photoplethysmography (rPPG)video analysispulse rate variability (PRV)periodic variance maximization (PVM)peak detection |
| spellingShingle | Peixi Li Yannick Benezeth Richard Macwan Keisuke Nakamura Randy Gomez Chao Li Fan Yang Video-Based Pulse Rate Variability Measurement Using Periodic Variance Maximization and Adaptive Two-Window Peak Detection Sensors remote photoplethysmography (rPPG) video analysis pulse rate variability (PRV) periodic variance maximization (PVM) peak detection |
| title | Video-Based Pulse Rate Variability Measurement Using Periodic Variance Maximization and Adaptive Two-Window Peak Detection |
| title_full | Video-Based Pulse Rate Variability Measurement Using Periodic Variance Maximization and Adaptive Two-Window Peak Detection |
| title_fullStr | Video-Based Pulse Rate Variability Measurement Using Periodic Variance Maximization and Adaptive Two-Window Peak Detection |
| title_full_unstemmed | Video-Based Pulse Rate Variability Measurement Using Periodic Variance Maximization and Adaptive Two-Window Peak Detection |
| title_short | Video-Based Pulse Rate Variability Measurement Using Periodic Variance Maximization and Adaptive Two-Window Peak Detection |
| title_sort | video based pulse rate variability measurement using periodic variance maximization and adaptive two window peak detection |
| topic | remote photoplethysmography (rPPG) video analysis pulse rate variability (PRV) periodic variance maximization (PVM) peak detection |
| url | https://www.mdpi.com/1424-8220/20/10/2752 |
| work_keys_str_mv | AT peixili videobasedpulseratevariabilitymeasurementusingperiodicvariancemaximizationandadaptivetwowindowpeakdetection AT yannickbenezeth videobasedpulseratevariabilitymeasurementusingperiodicvariancemaximizationandadaptivetwowindowpeakdetection AT richardmacwan videobasedpulseratevariabilitymeasurementusingperiodicvariancemaximizationandadaptivetwowindowpeakdetection AT keisukenakamura videobasedpulseratevariabilitymeasurementusingperiodicvariancemaximizationandadaptivetwowindowpeakdetection AT randygomez videobasedpulseratevariabilitymeasurementusingperiodicvariancemaximizationandadaptivetwowindowpeakdetection AT chaoli videobasedpulseratevariabilitymeasurementusingperiodicvariancemaximizationandadaptivetwowindowpeakdetection AT fanyang videobasedpulseratevariabilitymeasurementusingperiodicvariancemaximizationandadaptivetwowindowpeakdetection |