心率是一種常見的臨床指標，靜態心率(Resting Heart Rate)是指人體在休息狀態下的心跳速度，反映著身體的當下狀態。大多數學者認為當靜態心率過快時，人體健康可能出現問題。若能有效且方便的量測日常的靜態心率，將可有效的提醒受測者生理狀態的變化，預防心血管疾病死亡的發生。發展無感的非接觸式量測技術是未來技術的趨勢，可以減少受測者量測過程中的不適與活動限制。在網路涵蓋率提高的影響下，網路攝影機的安裝相對方便，並可以達到遠距連線，具有高便利性與市場商機。
本論文將以床邊生理監控為主軸，嘗試利用網路攝影機為開發平台，建構出一套適用於長期監控的非接觸式脈搏量測與移動狀態偵測系統。藉由網路攝影機鏡頭拍攝影像，透過膚色辨識影像處理演算法追蹤並定位出人臉或膚色部位的位置，擷取膚色區塊的rPPG (remote Photoplethysmography)訊號，推算出脈搏率。此外，本論文也透過分析量測部位的位置變化，偵測出受試者當下的移動狀態。並將移動狀態轉換為移動參考指標以避免推算含有大量移動雜訊的rPPG脈搏訊號，提升即時脈搏率量測準確度。
經過模擬真實床邊監控的日間與夜間量測實驗證實，所有受試者在臉部動態量測實驗中，其脈搏率誤差範圍為+4.40 bpm至-5.05 bpm。並可依照受試者移動幅度大小，偵測並分類出移動狀態。而在後頸部靜態量測實驗中，其脈搏率誤差範圍為+4.30 bpm至-4.36 bpm。實驗結果顯示，本論文成功於網路攝影機平台上建構出一套脈搏與活動狀態監控系統，並有效降低偶發性移動對準確度的影響。

A resting heart rate refers to the heart rate of a body at rest, which reflects the current state of health. Most scholars believe that a rapid resting heart rate may adversely affect human health. If we can conveniently measure the daily resting heart rate, we can effectively notify the subjects of sudden changes in physiological status. The development of non-contact measurement technology is a future trend. This new development can reduce the discomfort and activity limitations of the subject during measurement. Under the influence of increasing network coverage, the installation of IP-Cameras is relatively convenient and long-distance connections can be achieved.
In this thesis, we use an IP-Camera to construct a contactless pulse rate measurement and motion status monitoring system. The remote photoplethysmography (rPPG) signal of the region of interest (ROI) tracked through complexion tracking algorithm is obtained to calculate the pulse rate. In addition, we detected the subject's motion status and proposed a motion reference index to avoid estimating the rPPG pulse signal containing motion artifacts.
Experiments performed in the daytime and nighttime to simulate bedside monitoring have all confirmed that the error range of participants’ pulse rate for facial dynamic movement experiment is between +4.40 to -5.05 bpm. In the posterior neck static experiment, the error range of pulse rate is +4.30 to -4.36 bpm. The experimental results convey that this thesis not only successfully constructed a pulse rate and motion monitoring system on an IP-Camera platform but also improved the impact of accidental movement on a subjects’ pulse rate.

[1] K. Fox, N. Danchin, J. Lopez Sendon, J. Tardif and M. Tendera, “Resting Heart Rate in Cardiovascular Disease,” J. Am. Coll. Cardiol., vol. 50, no. 9, pp. 823–830, 2007.
[2] M. T. Cooney, E. Vartiainen, T. Laakitainen, A. Juolevi, A. Dudina, and I. M. Graham, “Elevated resting heart rate is an independent risk factor for cardiovascular disease in healthy men and women,” Am. Heart J., vol. 159, no. 4, p. 612–619.e3, 2010.
[3] 部會新聞, “國家通訊傳播委員會審議通過「普及偏鄉寬頻接取基礎建設補助作業要點」，經由前瞻基礎建設特別預算及業者合力投入，建構偏鄉高速寬頻網絡，帶動高速寬頻之創新服務至偏鄉,” 行政院, 2017. [Online]. Available: https://www.ey.gov.tw/Page/AE5575EAA0A37D70/0ae9413d-adb3-4e6d-983a-714676110b54.
[4] A. B. Hertzman, “The blood supply of various skins areas as estimated by the photoelectric plethysmograph,” Am. J. Physiol., vol. 124, pp. 328–340, 1938.
[5] C. Z. Wang and Y. P. Zheng, “Home-telecare of the elderly living alone using an new designed ear-wearable sensor,” in Proc. 5th Int. Workshop on Wearable and Implantable Body Sensor Networks, BSN2008, in conjunction with the 5th Int. Summer School and Symp. on Medical Devices and Biosensors, ISSS-MDBS 2008, 2008, pp. 71–74.
[6] S. Vogel, M. Hülsbusch, T. Hennig, V. Blazek, and S. Leonhardt, “In-ear vital signs monitoring using a novel microoptic reflective sensor,” IEEE Trans. Inf. Technol. Biomed., vol. 13, no. 6, pp. 882–889, 2009.
[7] C. Takano and Y. Ohta, “Heart rate measurement based on a time-lapse image,” Med. Eng. Phys., vol. 29, no. 8, pp. 853–857, 2007.
[8] G. Cennini, J. Arguel, K. Akşit, and A. VanLeest, “Heart rate monitoring via remote photoplethysmography with motion artifacts reduction,” Opt. Express, vol. 18, no. 5, p. 4867, 2010.
[9] E. Jonathan and M. J. Leahy, “Cellular phone-based photoplethysmographic imaging,” J. Biophotonics, vol. 4, no. 5, pp. 293–296, 2011.
[10] D. Shao, Y. Yang, C. Liu, F. Tsow, H. Yu, and N. Tao, “Noncontact monitoring breathing pattern, exhalation flow rate and pulse transit time,” IEEE Trans. Biomed. Eng., vol. 61, no. 11, pp. 2760–2767, 2014.
[11] M. C. Li and Y. H. Lin, “A real-time non-contact pulse rate detector based on smartphone,” 4th Int. Symp. Next-Generation Electron. IEEE ISNE 2015, 2015.
[12] Y. C. Lin, N. K. Chou, G. Y. Lin, M. H. Li, and Y. H. Lin, “A real-time contactless pulse rate and motion status monitoring system based on complexion tracking,” Sensors (Switzerland), vol. 17, no. 7, 2017.
[13] T. Tamura, Y. Maeda, M. Sekine, and M. Yoshida, “Wearable Photoplethysmographic Sensors—Past and Present,” Electronics, vol. 3, no. 2, pp. 282–302, 2014.
[14] The Life Sensing Technology on your HELO, “Principle of PPG,” Helo band. [Online]. Available: http://www.buyhelo.com.au/helo-science/.
[15] H. Xiaowen and L. Muqing, “PPG6350 - Pulse Oximeter Based Heart Rate Monitor,” Columbia University, 2014. [Online]. Available: http://www.ee.columbia.edu/~kinget/EE6350_S14/PPG6350_Web/index.html.
[16] W. Verkruysse, L. O. Svaasand, and J. S. Nelson, “Remote plethysmographic imaging using ambient light,” Opt. Express, vol. 16, no. 26, p. 21434, 2008.
[17] “Fujitsu Laboratories Develops Real-Time Pulse Monitor Using Facial Imaging : Fujitsu Global,” 2013. [Online]. Available: http://www.fujitsu.com/global/news/pr/archives/month/2013/20130318-01.html.
[18] S. Paschalakis and M. Bober, “A low cost FPGA system for high speed face detection and tracking,” Field-Programmable Technol. (FPT), 2003. Proceedings. 2003 IEEE Int. Conf., pp. 214–221, 2003.
[19] T. Nguyen, “Real-Time Face Detection and Tracking,” Electrical and Computer Engineering of Cornell University. December, 2012.
[20] Y. C. Lin and Y. H. Lin, “A study of color illumination effect on the SNR of rPPG signals,” Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, pp. 4301–4304, 2017.
[21] S. Kwon, J. Kim, D. Lee, and K. Park, “ROI analysis for remote photoplethysmography on facial video,” Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, vol. 2015–November, pp. 4938–4941, 2015.
[22] D. McDuff, S. Gontarek, and R. W. Picard, “Improvements in remote cardiopulmonary measurement using a five band digital camera,” IEEE Trans. Biomed. Eng., vol. 61, no. 10, pp. 2593–2601, 2014.
[23] L. Terminelli, F. Carpignano, F. Carpignano, S. Merlo, P. A. Kyriacou, “Photoplethysmography and electrocardiography for real time evaluation of pulse transit time,” Fotonica AEIT Ital. Conf. Photonics Technol., pp. 2–5, 2014.
[24] Y. Chen, C. Lin, Y. Lin, and C. Zhao, “Non-invasive detection of alcohol concentration based on photoplethysmogram signals,” pp. 188–193, 2017.
[25] Z. H. Al-Tairi, R. W. Rahmat, M. Iqbal Saripan, and P. S. Sulaiman, “Skin segmentation using YUV and RGB color spaces,” J. Inf. Process. Syst., vol. 10, no. 2, pp. 283–299, 2014.
[26] G. DeHaan and V. Jeanne, “Robust pulse-rate from chrominance-based rPPG,” vol. 60, no. 10, pp. 1–9, 2013.
[27] T. Wartzek and C. Bruser, “Modeling of motion artifacts in contactless heart rate measurements,” Comput. Cardiol. (2010)., no. 1, pp. 931–934, 2013.
[28] Y. C. Lin and Y. H. Lin, “Step Count and Pulse Rate Detection Based on the Contactless Image Measurement Method,” IEEE Trans. Multimed., vol. 9210, no. c, 2018.
[29] “NONIN 4100 BLUETOOTH PATIENT MODULE - Turner Medical.” [Online].Available: http://www.turnermedical.com/NONIN_4100_BLUETOO
TH_PATIENT_MODULE_p/nonin_4100.htm.
[30] x-io Technologies, “x-IMU with Housing and Battery,” x-IMU PURCHASE, 2016. [Online]. Available: http://x-io.co.uk/x-imu/.