生命徵象檢測是急救的第一步，OCHA(out-of-hospital cardiac arrest，到院前心肺功能停止)患者在心跳停止時會有瀕死喟嘆式呼吸的反應，會讓旁人誤判患者有呼吸而不需要進CPR(cardiopulmonary resuscitation，心肺復甦術)，導致錯過急救時間。目前判別是否有脈搏的方法還是使用手指觸摸頸部的方式，但即使是專業的醫療護人員都無法短時間內正確地判斷。
為了提供使用者一個可隨身攜帶的生命徵象檢測器，在本論文中，使用新穎的非接觸式脈搏量測技術計算脈搏訊號並實現於僅支援YUV影像的智慧型手機，我們透過脈搏在短時間內具有週期性的特性區分有脈搏與無脈搏對象，且能以膚色深淺判斷是否要開啟手機閃光燈以添加額外光源，對膚色較深的對象可提升訊號SNR(signal-to-noise ratio)。
本論文的實驗在一般實驗室環境進行，在活體皮膚檢測實驗中，21位活體受測者在手機以支架固定的測狀態下，準確度為100%。在手持手機量測的狀態下，準確度為94%，實驗結果顯示本論文提出的方法與近年來的研究方法比較，在活體皮膚辨識有較高的準確度。

The detection of vital signs is the first step in first aid. OCHA (out-of-hospital cardiac arrest) patients will have agonal respiration when the heart stops beating. It makes people misjudge the situation of the patient. Current method of pulse checking is using fingers to touch the neck. However, even a professional medical staff cannot recognize it correctly in a short time.
In order to provide the user with a livingness detector that can be carried around, we use the smartphone as a development platform. In this paper, we use novel non-contact pulse measurement techniques to calculate the pulse signal and implement it in smartphones which only supports YUV image. Detecting livingness by using characteristics of pulse signal, and there is an auto flashlight function which can add extra light source if the skin color is dark. It would increase the SNR(signal-to-noise ratio).
The proposed method has only been validated in lab conditions but not in real clinical conditions. The accuracies are 100% and 94% in the fixed-holding and hand-held experiment, respectively. The result shows that the propose method outperforms recent studies.

[1] G. Linderoth et al., “Challenges in out-of-hospital cardiac arrest - A study combining closed-circuit television (CCTV) and medical emergency calls,” Resuscitation, vol. 96, pp. 317–322, 2015.
[2] F. J. Ochoa, E. Ramalle-Gómara, J. M. Carpintero, A. García, and I. Saralegui, “Competence of health professionals to check the carotid pulse,” Resuscitation, vol. 37, no. 3, pp. 173–175, 1998.
[3] J. Bahr, H. Klingler, W. Panzer, H. Rode, and D. Kettler, “Skills of lay people in checking the carotid pulse,” Resuscitation, vol. 35, no. 1, pp. 23–26, 1997.
[4] B. Eberle, W. F. Dick, T. Schneider, G. Wisser, S. Doetsch, and I. Tzanova, “Checking the carotid pulse check: Diagnostic accuracy of first responders in patients with and without a pulse,” Resuscitation, vol. 33, no. 2, pp. 107–116, 1996.
[5] L. White et al., “Dispatcher-assisted cardiopulmonary resuscitation: Risks for patients not in cardiac arrest,” Circulation, vol. 121, no. 1, pp. 91–97, 2010.
[6] D. J. McDuff, E. B. Blackford, and J. R. Estepp, “The Impact of Video Compression on Remote Cardiac Pulse Measurement Using Imaging Photoplethysmography,” Proc. - 12th IEEE Int. Conf. Autom. Face Gesture Recognition, FG 2017 - 1st Int. Work. Adapt. Shot Learn. Gesture Underst. Prod. ASL4GUP 2017, Biometrics Wild, Bwild 2017, Heteroge, pp. 63–70, 2017.
[7] W. Verkruysse, L. O. Svaasand, and J. S. Nelson, “Remote plethysmographic imaging using ambient light,” Opt. Express, vol. 16, no. 26, p. 21434, 2008.
[8] 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.
[9] G. DeHaan and V. Jeanne, “Robust pulse rate from chrominance-based rPPG,” IEEE Trans. Biomed. Eng., vol. 60, no. 10, pp. 2878–2886, 2013.
[10] 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.
[11] L. Feng, S. Member, L. Po, and S. Member, “Motion-Resistant Remote Imaging Photoplethysmography Based on the Optical Properties of Skin,” vol. 25, no. 5, pp. 879–891, 2015.
[12] W. Wang, A. C. DenBrinker, S. Stuijk, and G. DeHaan, “Color-Distortion Filtering for Remote Photoplethysmography,” Proc. - 12th IEEE Int. Conf. Autom. Face Gesture Recognition, FG 2017 - 1st Int. Work. Adapt. Shot Learn. Gesture Underst. Prod. ASL4GUP 2017, Biometrics Wild, Bwild 2017, Heteroge, pp. 71–78, 2017.
[13] G. Gibert, D. D’Alessandro, and F. Lance, “Face detection method based on photoplethysmography,” Adv. Video Signal Based Surveill. (AVSS), 2013 10th IEEE Int. Conf., pp. 449–453, 2013.
[14] A. Hyvarinen, “A family of fixed-point algorithms for independent component analysis,” 1997 IEEE Int. Conf. Acoust. Speech, Signal Process., vol. 5, no. 3, pp. 3917–3920, 1997.
[15] W. Wang, S. Stuijk, and G. DeHaan, “Unsupervised subject detection via remote PPG,” IEEE Trans. Biomed. Eng., vol. 62, no. 11, pp. 2629–2637, 2015.
[16] 游舜傑, “基於智慧型手機之非接觸式脈搏量測與活體皮膚辨識,” 國立臺灣科技大學, 2017.
[17] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Proc. 2001 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognition. CVPR 2001, vol. 1, p. I-511-I-518, 2001.
[18] B. D. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision,” Imaging, vol. 130, no. x, pp. 674–679, 1981.
[19] Sony, “XperiaTM Z5 Premium,” 2016. [Online]. Available: http://www.sonymobile.com/global-en/products/phones/xperia-z5-premium/.
[20] E. J. Benjamin et al., Heart Disease and Stroke Statistics—2018 Update: A Report From the American Heart Association. 2018.
[21] M. L. Weisfeldt et al., “Ventricular Tachyarrhythmias after Cardiac Arrest in Public versus at Home,” N. Engl. J. Med., vol. 364, no. 4, pp. 313–321, 2011.
[22] F. Lapostolle, P. LeToumelin, J. M. Agostinucci, J. Catineau, and F. Adnet, “Basic cardiac life support providers checking the carotid pulse: Performance, degree of conviction, and influencing factors,” Acad. Emerg. Med., vol. 11, no. 8, pp. 878–880, 2004.
[23] G. Balakrishnan, F. Durand, and J. Guttag, “Detecting pulse from head motions in video,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 3430–3437, 2013.
[24] T. Tamura, Y. Maeda, M. Sekine, and M. Yoshida, “Wearable Photoplethysmographic Sensors—Past and Present,” Electronics, vol. 3, no. 2, pp. 282–302, 2014.
[25] Y. Sun and N. Thakor, “Photoplethysmography Revisited: From Contact to Noncontact, from Point to Imaging,” IEEE Trans. Biomed. Eng., vol. 63, no. 3, pp. 463–477, 2016.
[26] 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.
[27] 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.
[28] F. U. S. Mattace-Raso et al., “Determinants of pulse wave velocity in healthy people and in the presence of cardiovascular risk factors: ‘Establishing normal and reference values,’” Eur. Heart J., vol. 31, no. 19, pp. 2338–2350, 2010.
[29] L. M. VanBortel et al., “Expert consensus document on the measurement of aortic stiffness in daily practice using carotid-femoral pulse wave velocity,” J. Hypertens., vol. 30, no. 3, pp. 445–448, 2012.
[30] J. Allen and A. Murray, “Age-related changes in peripheral pulse timing characteristics at the ears, fingers and toes,” J. Hum. Hypertens., vol. 16, no. 10, pp. 711–717, 2002.
[31] G. Bradski and A. Kaehler, Projection and 3D Vision. 2008.
[32] “YUV - Wikipedia.” [Online]. Available: https://en.wikipedia.org/wiki/YUV.
[33] R. E. Kalman, “A New Approach to Linear Filtering and Prediction Problems,” Trans. ASME, J. Basic Eng., vol. 82, no. 1, pp. 35–45, 1960.
[34] A. Treesirichod, S. Chansakulporn, and P. Wattanapan, “Digital Photographic RGB Scores used for the Evaluation of Skin Color,” vol. 1, no. 1, pp. 17–20, 2015.