隨著行動運算演進，智慧型手持裝置效能越來越好，可做為生理監測平台發展。本論文研究，為了能讓心率量測更加方便及舒適，使用非接觸式的影像PPG脈搏量測方式，在智慧型手持裝置上實作開發出應用程式。使用者不用配戴任何感測器，只需要將智慧型手持裝置放在使用者臉部前方，即開始追蹤臉部影像中的ROI(感興趣區域Region of Interest)，利用攝影機觀測到人體皮膚亮度的變化，進而提取ROI中的影像為PPG訊號。為了有效降低移動雜訊，本論文使用帶通濾波器及卡爾曼濾波器，可以降低訊號中的移動雜訊並即時地計算出脈搏率。
在準確度驗證部份使用FDA認證過的生理監視器驗證。在實驗1中，受試者被要求坐著、看著智慧型手機靜態量測。然而在實驗2，受試者額外再被要求頭部規律地轉動。實驗1及2的量測誤差標準差分別為2.2 bpm及3.6 bpm。本研究提出的方法，能有效抑制移動雜訊，改善脈搏偵測準確度。

As mobile computing technology evolves, performance of smartphone is getting better to be a health monitoring platform. To make heart rate measurement more convenient and comfortable, we adopted remote PPG method and developed pulse rate monitor app based on smartphone. User doesn’t need to wear any sensor while measuring. Just put the smartphone in front of user’s face. It will automatically start tracking face as ROI (Region of Interest) in the image frame. And detect the brightness change of facial skin by camera. Then extract PPG signal in the ROI. To suppress motion artifacts in PPG signal effectively, we use band-pass filter and Kalman filter. By signal processing, we can extract pule rate at real-time.
The proposed pulse monitor app was evaluated by compared with FDA approved vital signs monitor. During experiment 1, subjects were asked to sit still and look at the smartphone. While in experiment 2, subjects were additionally asked to move their heads regularly. The standard deviation of experiment 1 and 2 were 2.2 bpm and 3.6 bpm respectively. Our proposed method could reduce motion artifacts and improve peak detection accuracy.

[1] Kannel, W. B., et al. "Heart rate and cardiovascular mortality: the Framingham Study." American heart journal 113.6 (1987): 1489-1494.
[2] Weinstein, M. C., and Stason, W. B. "Cost-effectiveness of interventions to prevent or treat coronary heart disease." Annual review of public health 6.1 (1985): 41-63.
[3] Pearson, T. A., et al. "Markers of inflammation and cardiovascular disease application to clinical and public health practice: a statement for healthcare professionals from the centers for disease control and prevention and the American Heart Association." Circulation 107.3 (2003): 499-511.
[4] Larks, S. D., and Abdul-Karim, R. "The Normal Fetal Electrocardiogram, with a Pro-Posed System of Standardized Terminology." Bio-Medical Electronics, IRE Transactions on 8.2 (1961): 136-139.
[5] Hertzman, A. B., "The blood supply of various skin areas as estimated by the photoelectricplethysmograph." publisher not identified, 1938.
[6] Boulos, M. N., et al. "How smartphones are changing the face of mobile and participatory healthcare: an overview, with example from eCAALYX." Biomedical engineering online 10.1 (2011): 24.
[7] Scully, C., et al. "Physiological parameter monitoring from optical recordings with a mobile phone." Biomedical Engineering, IEEE Transactions on 59.2 (2012): 303-306.
[8] 蘋果公司。穿戴式裝置Apple watch。民國104年5月，取自:
https://www.apple.com/tw/watch/technology/
[9] Pavlidis, I., et al. "Interacting with human physiology." Computer Vision and Image Understanding 108.1 (2007): 150-170.
[10] Li, M. C., and Lin, Y. H., "A real-time non-contact pulse rate detector based on smartphone." Next-Generation Electronics (ISNE), 2015 International Symposium on. IEEE, 2015.
[11] Poh, M. Z., McDuff, D. J., and Picard, R. W. "Non-contact, automated cardiac pulse measurements using video imaging and blind source separation." Optics express 18.10 (2010): 10762-10774.
[12] Kwon, S., Kim, H., and Park, K. S. "Validation of heart rate extraction using video imaging on a built-in camera system of a smartphone." Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE. IEEE, 2012.
[13] Feng, L., et al. "Motion artifacts suppression for remote imaging photoplethysmography." Digital Signal Processing (DSP), 2014 19th International Conference on. IEEE, 2014.

[14] Lucas, B. D., and Kanade, T. "An iterative image registration technique with an application to stereo vision." IJCAI. Vol. 81. 1981.
[15] Van Der Merwe, R. "Sigma-point Kalman filters for probabilistic inference in dynamic state-space models." Diss. Oregon Health & Science University, 2004.
[16] Liu, S. H., Chang, K. M., and Yang, S. C. "Using a Kalman filter to compensate for photoplethysmogram artifacts when monitoring CT examinations." Biomedical Engineering and Informatics, 2009. BMEI'09. 2nd International Conference on. IEEE, 2009.
[17] 中華民國衛生福利部。民國102年主要死因分析。民國104年5月，取自: http://www.mohw.gov.tw/MOHW_Upload/doc/民國102年主要死因分析_0045347003.doc
[18] 網路智慧新臺灣政策白皮書。智慧健康照護行動計畫。民國104年5月，取自: http://vbook.join.gov.tw/content/smart/health.html
[19] Allen, J. "Photoplethysmography and its application in clinical physiological measurement." Physiological measurement 28.3 (2007): R1.
[20] Tamura, T., et al. "Wearable Photoplethysmographic Sensors—Past and Present." Electronics 3.2 (2014): 282-302.
[21] Webster, J. G. "Medical instrumentation." Application and Design, Houghton Mifflin Company, 1992.
[22] Kawasaki (2013, March 18), Fujitsu Laboratories Develops Real-Time Pulse Monitor Using Facial Imaging, Fujitsu Laboratories Ltd. Retrieved April 1, 2015, from http://www.fujitsu.com/global/about/resources/news/press-releases/2013/0318-01.html
[23] Android Low-Level系統架構圖, https://source.android.com/devices/
[24] Android Camera 架構圖, https://source.android.com/devices/camera/index.html
[25] Android Camera 組成圖, https://source.android.com/devices/camera/camera3.html
[26] OpenCV, http://zh.wikipedia.org/wiki/OpenCV
[27] Viola, P., and Jones, M. "Robust real-time object detection." International Journal of Computer Vision 4 (2001): 34-47.
[28] OpenCV documentation, Haar Feature-based Cascade Classifier for Object Detection, http://docs.opencv.org/modules/objdetect/doc/cascade_classification.html
[29] OpenCV documentation, Lucas-Kanade Optical Flow in OpenCV,
http://docs.opencv.org/master/d7/d8b/tutorial_py_lucas_kanade.html
[30] Bradski, G., and Kaehler, A. "Learning OpenCV: computer vision with the OpenCV library." O'Reilly USA (2008).
[31] Kalal, Z., Mikolajczyk, K., and Matas, J. "Face-TLD: Tracking-learning-detection applied to faces." Image Processing (ICIP), 2010 17th IEEE International Conference on. IEEE, 2010.
[32] 卡爾曼濾波器的應用: 2D滑鼠座標追蹤,
http://www.morethantechnical.com/2011/06/17/simple-kalman-filter-for-tracking-using-opencv-2-2-w-code/
[33] Verkruysse, W., Svaasand, L. O., and Nelson, J. S. "Remote plethysmographic imaging using ambient light." Optics express 16.26 (2008): 21434-21445.
[34] Kalman, R. E. "A new approach to linear filtering and prediction problems." Journal of Fluids Engineering 82.1 (1960): 35-45.
[35] ViTrox Technologies。市面上以智慧型手持裝置為平台的心率計算應用程式:我的心跳。Google Play。民國104年5月，取自: https://play.google.com/store/apps/details?id=com.vitrox.facion.gui&hl=zh_TW
[36] Buda, A., and Jarynowski., A. Life time of correlations and its applications.[Vol. 1]. 2010.
[37] Prawiro, E. A. P. J., et al. "A heart rate detection method for low power exercise intensity monitoring device." Bioelectronics and Bioinformatics (ISBB), 2014 IEEE International Symposium on. IEEE, 2014.
[38] Pan, J., and Tompkins, W. J. "A real-time QRS detection algorithm." Biomedical Engineering, IEEE Transactions on 3 (1985): 230-236.
[39] 李少成. 一種消除攝像頭條紋的方法: 中國, 200610157025.8[P]. 2008-06-04 [2015-05].