近年來非接觸式生理訊號量測呈現蓬勃發展的趨勢，儼然漸漸地成為了社會大眾用於評估個體健康的重要方法，其中心率的參數是最常作為個人健康的重要指標。在傳統的生理訊號檢測方法，可能會導致使用者分心或不適。相反的，透過遠距離非接觸式脈搏量測可以在不干擾使用者的情況下進行心率的量測。
根據過往的研究中，基於影像的非接觸式脈搏量測需要在良好的環境進行量測，以避免移動雜訊與光源雜訊 所產生的誤差，但在現實的環境中處理因運動或光源變化所產生的干擾是無可避免的。本論文提出了一套降低光源變化干擾的演算法，比起過往的研究，在光源變化下更容易準確的量測到心率。根據實驗結果，在固定頻率光源變化環境下，本論文的平均絕對誤差(Mean Absolute Error, MAE)與均方根誤差(Root Mean Square Error, RMSE)分別為3.35 bpm與4.47 bpm，Success Rate-5/10的平均分別為0.83/0.91。以影片作為非固定頻率光源變化時，本論文的平均絕對誤差(Mean Absolute Error, MAE)與均方根誤差(Root Mean Square Error, RMSE)分別為1.26 bpm與1.71 bpm，Success Rate-5/10的平均分別為0.96/0.98。

In recent years, non-contact measurement of physiological signals has been developed vigorously and become a powerful method to evaluate personal health, and the heart rate is usually considered as an important indicator. The traditional methods for detecting physiological signals may make the user distracted or uncomfortable, while the non-contact method can measure the heart rate without interfering the user.
According to previous research, image-based and non-contact pulse rate measurement needs to be conducted in a good environment to avoid errors caused by movement artifacts and light source artifacts. However, in a real environment, dealing with interferences from movement or light source changes is inevitable. This thesis proposes an algorithm to reduce the interference of light source changes. Compared with previous studies, it provides higher accuracy of pulse rate measurement as light source changes. According to the experimental results, under the environment of fixed frequency light source, the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of this thesis are 3.35 bpm and 4.47 bpm, respectively. The average of Success Rate-5/10 is 0.83/0.91 respectively. When under the environment as a non-fixed frequency light source, the MAE and RMSE of this paper are 1.26 bpm and 1.71 bpm, respectively. The averages of Success Rate-5/10 are 0.96/0.98 respectively.

[1] 內政部警政署, “A1類道路交通事故－按肇事原因分類,” [Online]. Available: http://www.npa.gov.tw.
[2] 衛生福利部統計處, “死因統計,” [Online]. Available: https://dep.mohw.gov.tw/DOS/np-1775-113.html.
[3] 台大醫院臨床試驗中心, “醫學統計諮詢服務,” [Online]. Available: https://www.ntuh.gov.tw/NCTRC/Fpage.action?muid=2942&fid=2768.
[4] W. Verkruysse, L. O. Svaasand, and J. S. Nelson, “Remote plethysmographic imaging using ambient light,” Opt. Express, vol. 16, no. 26, p. 21434, 2008
[5] M. Z. Poh, D. J. McDuff, and R. W. Picard, “Advancements in noncontact, multiparameter physiological measurements using a webcam,” IEEE Trans. Biomed. Eng., vol. 58, no. 1, pp. 7–11, 2011.
[6] L. Feng, L. M. Po, X. Xu, Y. Li, and R. Ma, “Motion-resistant remote imaging photoplethysmography based on the optical properties of skin,” IEEE Trans. Circuits Syst. Video Technol., vol. 25, no. 5, pp. 879–891, 2015.
[7] G. de Haan and V. Jeanne, “Robust pulse rate from chrominance-based rPPG,” IEEE Trans. Biomed. Eng., vol. 60, no. 10, pp. 2878–2886, 2013.
[8] W. Wang, S. Stuijk, and G. de Haan, “Exploiting spatial redundancy of image sensor for motion robust rPPG,” IEEE Trans. Biomed. Eng., vol. 62, no. 2, pp. 415–425, Feb 2015.
[9] H. Ghanadian, M. Ghodratigohar, and H. Al Osman, “A Machine Learning Method to Improve Non-Contact Heart Rate Monitoring Using an RGB Camera,” IEEE Access, vol. 6, pp. 57085–57094, 2018.
[10] M. Ghodratigohar, H. Ghanadian, and H. Al Osman, “A Remote Respiration Rate Measurement Method for Non-Stationary Subjects Using CEEMDAN and Machine Learning,” IEEE Sens. J., vol. 20, no. 3, pp. 1400–1410, 2020.
[11] X. Liu, X. Yang, J. Jin, and J. Li, “Self-adaptive signal separation for non-contact heart rate estimation from facial video in realistic environments,” Physiol. Meas., vol. 39, no. 6, 2018.
[12] M. Kumar, A. Veeraraghavan, and A. Sabharwal, “DistancePPG: Robust non-contact vital signs monitoring using a camera,” Biomed. Opt. Express, vol. 6, no. 5, p. 1565, 2015.
[13] R. M. Fouad, O. A. Omer, A. M. Ali, and M. H. Aly, “Refining ROI selection for real-time remote photoplethysmography using adaptive skin detection,” no. February, pp. 2–4, 2019.
[14] R. M. Fouad, O. A. Omer, and M. H. Aly, “Optimizing Remote Photoplethysmography Using Adaptive Skin Segmentation for Real-Time Heart Rate Monitoring,” IEEE Access, vol. 7, pp. 76513–76528, 2019.
[15] X. Li, J. Chen, G. Zhao, and M. Pietikäinen, “Remote heart rate measurement from face videos under realistic situations,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 4264–4271, 2014.
[16] D. Lee, J. Kim, S. Kwon, and K. Park, “Heart rate estimation from facial photoplethysmography during dynamic illuminance changes,” in Proc. 37th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, vol. 2015-Novem, pp. 2758–2761, 2015.
[17] K. Y. Lin, D. Y. Chen, and W. J. Tsai, “Face-Based Heart Rate Signal Decomposition and Evaluation Using Multiple Linear Regression,” IEEE Sens. J., vol. 16, no. 5, pp. 1351–1360, 2016.
[18] L. Xu, J. Cheng, and X. Chen, “Illumination variation interference suppression in remote PPG using PLS and MEMD,” Electron. Lett., vol. 53, no. 4, pp. 216–218, 2017.
[19] J. Cheng, X. Chen, L. Xu, and Z. J. Wang, “Illumination Variation-Resistant Video-Based Heart Rate Measurement Using Joint Blind Source Separation and Ensemble Empirical Mode Decomposition,” IEEE J. Biomed. Heal. Informatics, vol. 21, no. 5, pp. 1422–1433, 2017.
[20] B. F. Wu, Y. W. Chu, P. W. Huang, and M. L. Chung, “Neural Network Based Luminance Variation Resistant Remote-Photoplethysmography for Driver’s Heart Rate Monitoring,” IEEE Access, vol. 7, pp. 57210–57225, 2019.
[21] T. Tamura, Y. Maeda, M. Sekine, and M. Yoshida, “Wearable photoplethysmographic sensors—past and present,” Electron. , vol. 3, no. 2, pp. 282–302, 2014.
[22] K. Humphreys, T. Ward, and C. Markham, “Noncontact simultaneous dual wavelength photoplethysmography: A further step toward noncontact pulse oximetry,” Rev. Sci. Instrum., vol. 78, no. 4, 2007.
[23] 李明偉, “基於智慧型手機之YUV影像之非接觸式活體皮膚辨識方法,” 國立台灣科技大學, 2018.
[24] Y. C. Lin and Y. H. Lin, “Step Count and Pulse Rate Detection Based on the Contactless Image Measurement Method,” IEEE Trans. Multimed., vol. 20, no. 8, pp. 2223–2231, 2018.
[25] 呂明紘, “基於影像之非接觸心率與體溫量測系統,” 國立台灣科技大學, 2019.
[26] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 1, 2001.
[27] B. D. Lucas and T. Kanade, “Iterative Image Registration Technique With an Application To Stereo Vision.,” vol. 2, no. September, pp. 674–679, 1981.
[28] J. G. Allen, R. Y. D. Xu, and J. S. Jin, “Object Tracking Using CamShift Algorithm and Multiple Quantized Feature Spaces,” Reproduction, vol. 36, pp. 3–7, 2006.
[29] J. Shi and C. Tomasi, “Good Features,” Image (Rochester, N.Y.), pp. 593–600, 1994.
[30] J. F. Henriques, R. Caseiro, P. Martins, and J. Batista, “High-speed tracking with kernelized correlation filters,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 3, pp. 583–596, 2015.
[31] S. G. Mallat, “A theory for multiresolution signal decomposition: The wavelet representation,” Fundam. Pap. Wavelet Theory, vol. I, no. 7, pp. 494–513, 2009.
[32] C. Wang, T. Pun, and G. Chanel, “A comparative survey of methods for remote heart rate detection from frontal face videos,” Front. Bioeng. Biotechnol., vol. 6, no. MAY, pp. 1–16, 2018.
[33] “Polar H7” [Online]. Available: https://www.polar.com/tw-zh/products/accessories/H7_heart_rate_sensor.
[34] B. F. Wu, P. W. Huang, C. H. Lin, M. L. Chung, T. Y. Tsou, and Y. L. Wu, “Motion resistant image-photoplethysmography based on spectral peak tracking algorithm,” IEEE Access, vol. 6, pp. 21621–21634, 2018.
[35] "Samsung Galaxy S9+." [Online] Available: https://www.sumsung.com/tw/smartphones/galaxy-s9/specs/.
[36] W. Wang, A. C. den Brinker, S. Stuijk, and G. de Haan, ‘‘Algorithmic principles of remote PPG,’’ IEEE Trans. Biomed. Eng., vol. 64, no. 99, pp. 1479–1491, Jul. 2017.