使用消費型攝影機進行心率偵測的方法多是以人體的顏色或運動作為分析依據。當使用顏色為分析依據 (Color-Based) 時，透過對臉部區域取像素平均值進行頻域濾波，以提取最大能量之頻率作為心率值。而使用運動作為分析依據 (Motion-Based) 時，則是擷取並追蹤心臟跳動週期造成的頭部微小擺動軌跡，並由該軌跡訊號識別出與心跳對應的頻率成分。兩種方法皆有其侷限性，如 color-based 方法需要在臉部皮膚區域可被攝影機擷取的情況下才可適用， motion-based 方法則是對與心率無關的頭部運動較為敏感。我們將二者結合起來，以充分利用這些限制。我們進一步將臉部拆解為一些局部區塊，並比較不同的色彩空間以找出對於光源變化最具強健性的局部區塊及色彩通道，最後呈現出最可靠的心率量測結果。

The approaches for heartbeat detection using a consumer camera are based on either color or motion cues. When color is considered, the pixel values taken at facial region are averaged and temporally filtered to extract the frequency that corresponds to the maximal power. When motion is consider, the subtle head oscillation that accompanies cardiac cycles is captured and tracked, and from which the frequency components correspondent to heartbeats are identified. Both have limitations; for example, the color-based requires facial skin visible to the camera and the motion-based is sensitive to head motions irrelevant to cardiac cycles. We combine the two to leverage these limitations. We further decompose the face into component regions and compare different color spaces to identify the component region and color channel that is robust to illumination variation and renders the most reliable heartbeat measurement.

[1] L. Shan and M. Yu, “Video-based heart rate measurement using head motion tracking and ica,” in Image and Signal Processing (CISP), 2013 6th International Congress on, 2013.
[2] G.-S. Hsu and S.-M. Yeh, “Heterogeneous feature code for expression recognition,”Image Processing (ICIP), 2013 20th IEEE International Conference on, pp. 2407–2411, 2013.
[3] W. Verkruysse, L. O. Svaasand, and J. S. Nelson, “Remote plethysmographic imaging using ambient light,” Optics express, vol. 16, no. 26, pp. 21434–21445, 2008.
[4] S. Y. Chekmenev, A. A. Farag, W. M. Miller, E. A. Essock, and A. Bhatnagar,“Multiresolution approach for noncontact measurements of arterial pulse using thermal imaging,” in Augmented Vision Perception in Infrared, pp. 87–112, Springer, 2009.
[5] M.-Z. Poh, D. J. McDuff, and R. W. Picard, “Advancements in noncontact, multiparameter physiological measurements using a webcam,” Biomedical Engineering, IEEE Transactions on, vol. 58, no. 1, pp. 7–11, 2011.
[6] G. Balakrishnan, F. Durand, and J. Guttag, “Detecting pulse from head motions in video,” in Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp. 3430–3437, IEEE, 2013.
[7] A. S. Berson and H. V. Pipberger, “Skin-electrode impedance problems in electrocardiography,” American Heart Journal, vol. 76, no. 4, pp. 514 – 525, 1968.
[8] M. J. Burke and D. Gleeson, “A micropower dry-electrode ecg preamplifier,”Biomedical Engineering, IEEE Transactions on, vol. 47, pp. 155–162, Feb 2000.
[9] Y. K. Lim, K. K. Kim, and K. S. Park, “The ecg measurement in the bathtub using the insulated electrodes,” in Engineering in Medicine and Biology Society, 2004. IEMBS’04. 26th Annual International Conference of the IEEE, vol. 1, pp. 2383–2385, IEEE, 2004.
[10] Y. G. Lim, K. K. Kim, and S. Park, “Ecg measurement on a chair without conductive contact,” Biomedical Engineering, IEEE Transactions on, vol. 53, no. 5, pp. 956–959, 2006.
[11] Y. G. Lim, K. K. Kim, and K. S. Park, “Ecg recording on a bed during sleep without direct skin-contact,” Biomedical Engineering, IEEE Transactions on, vol. 54, no. 4,pp. 718–725, 2007.
[12] C. Li, J. Cummings, J. Lam, E. Graves, and W. Wu, “用雷達來遠程監測生命體徵,” Microwave Magazine, IEEE, pp. 47–55, Feb 2009.
[13] C. Liu, A. Torralba, W. T. Freeman, F. Durand, and E. H. Adelson, “Motion magnification,” in ACM SIGGRAPH 2005 Papers, SIGGRAPH ’05, (New York, NY, USA), pp. 519–526, ACM, 2005.
[14] H.-Y. Wu, M. Rubinstein, E. Shih, J. Guttag, F. Durand, and W. Freeman, “Eulerian video magnification for revealing subtle changes in the world,” ACM Transactions on Graphics (TOG), vol. 31, no. 4, p. 65, 2012.
[15] P. Buddharaju, I. T. Pavlidis, P. Tsiamyrtzis, and M. Bazakos, “Physiology-based face recognition in the thermal infrared spectrum,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 29, no. 4, pp. 613–626, 2007.
[16] M. Uřičař, V. Franc, and V. Hlavač, “Detector of facial landmarks learned by the structured output svm,” VISAPP, pp. 547–556, 2012.
[17] X. Zhu and D. Ramanan, “Face detection, pose estimation, and landmark localization in the wild,” in Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp. 2879–2886, IEEE, 2012.
[18] A. Asthana, S. Zafeiriou, S. Cheng, and M. Pantic, “Robust discriminative response map fitting with constrained local models,” in Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp. 3444–3451, IEEE, 2013.
[19] B. D. Lucas, T. Kanade, et al., “An iterative image registration technique with an application to stereo vision.,” in IJCAI, vol. 81, pp. 674–679, 1981.
[20] T. Brox, A. Bruhn, N. Papenberg, and J. Weickert, “High accuracy optical flow estimation based on a theory for warping,” in Computer Vision-ECCV 2004, pp. 25–36, Springer, 2004.
[21] J. S. Perez, E. Meinhardt-Llopis, and G. Facciolo, “Tv-l1 optical flow estimation,”Image Processing On Line, vol. 2013, pp. 137–150, 2013.
[22] B. K. Horn and B. G. Schunck, “Determining optical flow,” in 1981 Technical Symposium East, pp. 319–331, International Society for Optics and Photonics, 1981.
[23] J.-Y. Bouguet, “Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm,” Intel Corporation, vol. 5, 2001.
[24] M. J. Black and P. Anandan, “The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields,” Computer vision and image understanding, vol. 63, no. 1, pp. 75–104, 1996.
[25] A. L. Baggish and M. J. Wood, “Athlete’s heart and cardiovascular care of the athlete scientific and clinical update,” Circulation, vol. 123, no. 23, pp. 2723–2735, 2011.
[26] J.-F. Cardoso, “High-order contrasts for independent component analysis,” Neural computation, vol. 11, no. 1, pp. 157–192, 1999.