|
|
Heart Rate Measurements Using Principal Component Analysis and Overlapping Histgram Based on Video Signal |
Zhao Yantao*, Fu Meiling, Wang Bin, Zhang Xuguang, Li Xiaoli |
(School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China) |
|
|
Abstract The technique photo plethysmo graphy (PPG) shows that the light intensity has a periodical change with the change of blood volume. So the facial skin color will change a little along with the pulse. The technique can be used to measuring heart rate with many advantages, such as low cost, no contact and no electrode. This is helpful to remote medical monitoring and other fields. In this paper ordinary camera was used to collect human face videos. The principle components was extracted by calculating average values of green components on the three face regions through principal component analysis (PCA),and the noise was eliminated. The smoothing methods was used after PCA, and the detrending method was utilized in this paper. The peaks of signal were detected by the peak detecting method that was proposed in this work, which reduced detection of wrong peaks. Then the method of overlapping histogram statistics was used to get heart rate through calculating the intervals between peaks of the pulse signal. The proposed method was compared with results obtained from CMS-50D Finger clip type pulse oximeter of CONTEC company(measurement samples was 170)and MP150 multi-channel physiological recorder of BIOPAC company(measurement samples was 110)with the statistics method of Bland-Altma. Comparison of the results from CMS-50D with that from the proposed methods showed that the overlapping histogram statistics method reduced the standard deviations of the conformance assessment form 12.4 beats/min to 8 beats/min. Comparison of the results from MP150 with that from the proposed methods showed that the mean and the standard deviations of the conformance assessment was 1.81 and 3.18 bpm respectively, indicating the results were in good consistency.
|
Received: 12 October 2014
|
|
|
|
|
[1] 金晶晶, 王旭, 杨丹. 基于体震信号的心率测量方法[J]. 东北大学学报, 2009(2): 176- 179. [2] Cook S, Togni M, Schaub MC, et al. High heart rate: a cardiovascular risk factor? [J]. European Heart Journal, 2006, 27(20), 2387-2393. [3] Poh MZ, McDuff DJ, Picard RW, Non-contact, automated cardiac pulse measurements using video imaging and blind source separation [J].Optics Express, 2010,18: 10762-10774. [4] Wu Haoyu, Rubinstein M,Shih E, et al. Eulerian video magnification for revealing subtle changes in the world[J]. ACM Transactions on Graphics,2012,31(4):13-15. [5] Pavlidis I, Dowdall J, Sun NC, et al. Interacting with human physiology[J].Comput Vis Image Underst, 2007,108(1-2):150-170. [6] Garbey M, Sun N, Merla A, et al. Contact-free measurement of cardiac pulse based on the analysis of thermal imagery [J].IEEE Trans Biomed Eng,2007,54(8):1418-1426. [7] Fei Jin, Pavlidis I. Thermistor at a Distance: unobtrusive measurement of breathing[J]. IEEE Trans Biomed Eng,2010,57(4): 988-998. [8] Wieringa FP, Mastik F, Van AF, et al. Contactless multiple wavelength photoplethysmographic imaging: a first step toward “SPO2 camera” technology[J].Ann Biomed Eng,2005, 33(8): 1034-1041. [9] Humphreys K, Ward T, Markham C. Noncontact simultaneous dual wavelength photoplethysmography:A further step toward noncontact pulse oximetry[J].Rev Sci Instrum,2007, 78(4): 044304. [10] Takano C, Ohta Y. Heart rate measurement based on a time-lapse image[J].Med Eng Phys,2007, 29(8): 853-857. [11] Hu Sijung, Zheng Jia, Chouliaras V, et al. Feasibility of imaging photoplethysmography[C]//Hua Zhang, Zhanji Gui, eds. Proceedings of IEEE Conference on BioMedical Engineering and Informatics. Sanya: IEEE,2008:72-75. [12] Verkruysse W, Svaasand LO, Nelson JS. Remote plethysm-ographic imaging using ambient light[J].Opt Express,2008,16(26):21434-21445. [13] Cui WeiJia, Ostrander LE, Lee BY. In vivo reflectance of blood and tissue as a function of light wavelength[J]. IEEE Trans Biomed Eng,1990, 37(6): 632-639. [14] Poh MZ, McDuff DJ, Picard RW. Advancements in noncontact, multi-parameter physiological measurements using a webcam [J]. IEEE Trans Biomed Eng,2011,58(1):7-11. [15] Cheng Wenchang, Jhan Dingmao. A cascade classifier using Adaboost algorithm and support vector machine for pedestrian detection [C]//Tunstel E,Nahavandi S.IEEE International Conference on Systems, Man, and Cybernetics. Anchorage: IEEE, 2011:1430-1435. [16] 王建明,刘鑫璐.基于声表面波传感器阵列的气体鉴别算法研究[ J].测控技术,2013,32(11):63-67. [17] Mika PT, Perttu OR, Pasi AK. An advanced detrending method with application to HRV analysis [J]. IEEE Transactions on Biomedical Engineering. 2002, 49(2): 172-175. |
|
|
|