現今穿戴式裝置蓬勃發展，有許多在運動中進行即時心率量測的應用，但是穿戴式裝置本身仍存在著長時間使用會讓使用者感到被束縛住或不適，例如運動後流汗造成皮膚與穿戴式裝置產生過敏或感染。為了改善接觸式裝置的缺點，非接觸式心率量測逐漸受到重視，然而非接觸式量測很容易受到移動雜訊與光源變化影響，近年有許多學者針對移動雜訊消除進行研究並在運動器材上驗證其準確度，但大多數都是將其實現於個人電腦上，並利用RGB相機獲取影像進行心率計算。由於YUV影像格式在壓縮與傳輸上佔用較少頻寬的特性，近年來智慧型手機相機模組漸漸捨棄了RGB影像輸出，轉而只支援YUV影像格式，但YUV在彩度上有所壓縮，導致彩度上的脈搏訊號成分也會受到影響。
為了提供使用者一個方便攜帶且應用於運動器材上的非接觸式即時心率量測系統，本論文提出一套降低移動雜訊干擾的演算法，並實現在僅支援YUV影像的智慧型手機上，只需要利用手機前置鏡頭作為影像輸入來源進行即時運算，讓使用者可以藉由隨身攜帶的智慧型手機在運動情況也能量測心率。
本研究利用三種運動器材來驗證所提出的演算法準確度，在健身腳踏車、踏步機以及跑步機上所得到的平均絕對誤差(Mean Absolute Error, MAE)/均方根誤差(Root Mean Square Error, RMSE)分別為2.09/3.06 bpm、1.93/2.75 bpm與2.25/3.46 bpm，而Success Rate-5/10分別為0.88/0.94、0.86/0.93與0.88/0.95。相較過往的研究，在相對失真的訊號來源下也能夠精確的計算出即時心率。

Nowadays wearable devices for real-time heart rate measurement during exercise are flourishing, but wearing the devices for a long time may make the user feel uncomfortable or restrained. For example, sweating after exercise may cause allergies or infections in the skin area contacted to the wearable devices. In order to solve the shortcomings of contact devices, non-contact methods for pulse rate measurement have become the trend. However, non-contact methods are easily susceptible to motion artifact and light source changes. In recent years, researchers have proposed studies on different methods to reduce motion artifact and to solve the illumination problem, and most of the above-mentioned methods used a RGB camera to get the images for heart rate calculation with a personal computer. Since the YUV image format occupies less bandwidth in compression and transmission, the smart phone camera modules gradually abandon the RGB image output, and in turn only support the YUV image format. However, as the YUV is compressed in the chroma, which is a component of the pulse signal, the pulse signal component on the chroma will be affected.
In order to provide the user a portable and contactless system for real-time pulse rate detection on fitness equipment, this paper proposed a method to reduce the motion artifact on the smartphone that only supports YUV images. The system only uses the front lens of the smartphone as the image input source for real-time pulse rate detection, so that the user can measure heart rate with his/her own smartphone during exercise.
This study used three types of fitness equipment: the spinning bike, the stepper, and the treadmill to verify the accuracy of the proposed algorithm. The Mean Absolute Error (MAE)/Root Mean Square Error (RMSE) of pulse rate measurement on the spinning bike, the stepper, and the treadmill were 2.09/3.06 bpm, 1.93/2.75 bpm, and 2.25/3.46 bpm, respectively. In addition, Success Rate-5/10 was 0.88/0.94, 0.86/0.93 and 0.88/0.95, respectively. Compared with the previous studies, the real-time pulse rate can be accurately calculate under relatively distorted signal sources.

[1] TTR 台灣趨勢研究報告, "運動服務業發展趨勢" 台灣趨勢研究股份有限公司, 2017. [Online] Available: http://www.twtrend.com/upload/shares/a_15299856880.pdf.
[2] "促進健康體能的方法." 衛生福利部國民健康署, 2017. [Online] Available: https://www.hpa.gov.tw/Pages/Detail.aspx?nodeid=571&pid=882
[3] D. J. McDuff, E. B. Blackford, and J. R. Estepp, "The Impact of Video Compression on Remote Cardiac Pulse Measurement Using Imaging Photoplethysmography," in IEEE International Conference on Automatic Face & Gesture Recognition, 2017, pp. 63-70.
[4] C. Zhao, C. L. Lin, W. Chen, and Z. Li, "A Novel Framework for Remote Photoplethysmography Pulse Extraction on Compressed Videos," in IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018, pp. 1380-138009.
[5] W. Verkruysse, L. O. Svaasand, and J. S. Nelson, "Remote plethysmographic imaging using ambient light," Opt Express, vol. 16, no. 26, pp. 21434-21445, Dec. 2008.
[6] M. Poh, D. J. McDuff, and R. W. Picard, "Advancements in Noncontact, Multiparameter Physiological Measurements Using a Webcam," IEEE Transactions on Biomedical Engineering, vol. 58, no. 1, pp. 7-11, Jan. 2011.
[7] G. d. Haan and V. Jeanne, "Robust Pulse Rate From Chrominance-Based rPPG," IEEE Transactions on Biomedical Engineering, vol. 60, no. 10, pp. 2878-2886, Oct. 2013.
[8] M. C. Li and Y. H. Lin, "A real-time non-contact pulse rate detector based on smartphone," in International Symposium on Next-Generation Electronics 2015, pp. 1-3.
[9] L. Feng et al., "Motion-Resistant Remote Imaging Photoplethysmography Based on the Optical Properties of Skin," IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 5, pp. 879-891, May. 2015.
[10] W. Wang, S. Stuijk, and G. d. Haan, "A Novel Algorithm for Remote Photoplethysmography: Spatial Subspace Rotation," IEEE Transactions on Biomedical Engineering, vol. 63, no. 9, pp. 1974-1984, Sep. 2016.
[11] W. Wang, A. C. d. Brinker, S. Stuijk, and G. d. Haan, "Algorithmic Principles of Remote PPG," IEEE Transactions on Biomedical Engineering, vol. 64, no. 7, pp. 1479-1491, Jul. 2017.
[12] B. D. Lucas and T. Kanade, "An iterative image registration technique with an application to stereo vision," in Proc. International Joint Conference on Artificial Intelligence, 1981, pp. 674-679.
[13] R. Huang and L. Dung, "A motion-robust contactless photoplethysmography using chrominance and adaptive filtering," in IEEE Biomedical Circuits and Systems Conference (BioCAS), 2015, pp. 1-4.
[14] Y. C. Lin and Y. H. Lin, "Step Count and Pulse Rate Detection Based on the Contactless Image Measurement Method," IEEE Transactions on Multimedia, vol. 20, no. 8, pp. 2223-2231, Aug. 2018.
[15] B. F. Wu et al., "Motion Resistant Image-Photoplethysmography Based on Spectral Peak Tracking Algorithm," IEEE Access, vol. 6, pp. 21621-21634, Apr. 2018.
[16] T. Tamura, Y. Maeda, M. Sekine, and M. Yoshida, "Wearable photoplethysmographic sensors—past and present," Electronics, vol. 3, no. 2, pp. 282-302, Apr. 2014.
[17] Y. Sun and N. Thakor, "Photoplethysmography Revisited: From Contact to Noncontact, From Point to Imaging," IEEE Transactions on Biomedical Engineering, vol. 63, no. 3, pp. 463-477, Mar. 2016.
[18] L. Kong et al., "Non-contact detection of oxygen saturation based on visible light imaging device using ambient light," Opt Express, vol. 21, no. 15, pp. 17464-17471, Jul. 2013.
[19] K. Y. Lin, D. Y. Chen, and W. J. Tsai, "Image-Based Motion-Tolerant Remote Respiratory Rate Evaluation," IEEE Sensors Journal, vol. 16, no. 9, pp. 3263-3271, May. 2016.
[20] D. Shao et al., "Noncontact Monitoring Breathing Pattern, Exhalation Flow Rate and Pulse Transit Time," IEEE Transactions on Biomedical Engineering, vol. 61, no. 11, pp. 2760-2767, Nov. 2014.
[21] P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, pp. 511-518.
[22] Y. Freund and R. E. Schapire, "A decision-theoretic generalization of on-line learning and an application to boosting," Journal of computer and system sciences, vol. 55, no. 1, pp. 119-139, Aug. 1997.
[23] M. Danelljan, G. Häger, F. S. Khan, and M. Felsberg, "Discriminative Scale Space Tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 8, pp. 1561-1575, Aug. 2017.
[24] D. S. Bolme, J. R. Beveridge, B. A. Draper, and Y. M. Lui, "Visual object tracking using adaptive correlation filters," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010, pp. 2544-2550.
[25] "Miscellaneous Image Transformations-OpenCV." [Online] Available: https://docs.opencv.org/2.4/modules/imgproc/doc/miscellaneous_transformations.html
[26] "Samsung Galaxy S9+." [Online] Available: https://www.samsung.com/tw/smartphones/galaxy-s9/specs/.
[27] J. A. M. Basilio et al., "Explicit image detection using YCbCr space color model as skin detection," Applications of Mathematics and Computer Engineering, pp. 123-128, 2011.
[28] "Polar H7." [Online] Available: https://www.polar.com/tw-zh/products/accessories/H7_heart_rate_sensor.
[29] "Go Direct EKG." [Online] Available: https://www.vernier.com/products/sensors/ekg-sensors/gdx-ekg/.