生命徵象(Vital Signs)，是在維持人體基本生理功能時表現出來的徵象，這些測量結果可被用於評估個體的身體健康，其中心率與體溫是最常被醫生用來監控病人生理狀況的指標。
因此在醫院看診時，醫師常會要求先量測心率和體溫，藉由量測到的生理數值搭配病人說的症狀推斷病情，對症下藥。現今醫院在量測心率和體溫多使用接觸式的儀器進行，在量測過程中病人的活動會受到限制，且因為在醫院使用接觸式的儀器，會有接觸感染的風險。綜合上述問題，本論文建立一套基於影像之非接觸式心率與體溫量測系統，此系統只要透過普通的RGB相機和遠紅外光熱顯像儀，利用影像就能即時進行非接觸式的量測，讓使用者在自由活動的情況下也能夠量測心率與體溫，不僅能避免接觸感染的風險，也能給予病人更大的活動空間。
然而根據過往的研究，非接觸式心率訊號容易受到移動的干擾，在本篇研究中，提出一套降低移動干擾的演算法，比起過往的研究，在劇烈晃動的狀態下更精準的量測到心率，根據實驗結果，在使用者劇烈晃動的狀態下，其平均絕對誤差(Mean Absolute Error, MAE)與均方根誤差(Root Mean Square Error, RMSE)分別為4.42 BPM和6.21 BPM。
在體溫量測方面，為了能自動量測人臉的體溫，本論文也提出一套新的演算法，能夠自動地偵測熱顯像儀中人臉位置並進行追蹤，如此一來，使用者能夠自然地晃動，使得本系統在使用上能夠更加的舒適自在。根據最後的實驗結果，量測的體溫變化趨勢MAE和RMSE為0.375 °C和0.439 °C。

Vital Signs are signs that appear when maintaining the body's basic physiological functions. These measurements can be used to assess an individual's physical health, and in which the pulse rate and body temperature are the indicators most commonly used by doctors to monitor a patient's physical condition.
Therefore, when visiting a doctor, patients are often asked to measure the pulse rate and body temperature first and the doctor will infer the conditions and prescribe according to the patient’s physiological values and the described symptoms. Today hospitals usually adopt contact instruments for measuring the pulse rate and body temperature. Yet the patients’ activities are limited during the process of measuring, and there is a risk of contact infection by using contact instruments in the hospital. To solve the above problems, this paper establishes an image-based contactless pulse rate and body temperature measurement system. This system can instantly perform contactless measurements by using a normal RGB camera and a far-infrared photo thermal image camera, which allows the users to move freely while measuring the pulse rate and body temperature. Thus not only can the risk of contact infection be avoided but the patients are given bigger activity space.
However, according to previous research, contactless pulse rate signals are easily influenced by moving artifacts. This paper proposed an algorithm to reduce moving noise. Compared to previous research, the algorithm can measure the pulse rate more precisely in a state of severe shaking. According to the experimental results, the mean absolute error (MAE) and root mean square error (RMSE) are respectively 4.42 BPM and 6.21 BPM in a state where the user is shaking vigorously.
In body temperature measurement, the paper proposed a new algorithm on human face temperature measurement that can automatically detect and track human face positions with a thermal image camera. In this way, the user can move freely and use the system more comfortably. According to the final experimental results, the MAE and RMSE of the measured body temperature were 0.375 °C and 0.439 °C, respectively.

[1] "The World Health Organisation: Vital signs of WHO," [Online]. Available: https://www.bmj.com/content/310/6979/586
[2] W. Verkruysse, L. O. Svaasand, and J. S. Nelson, "Remote Plethysmographic Imaging Using Ambient Light," Optics express, vol. 16, no. 26, pp. 21434-21445, Dec. 2008
[3] 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.
[4] W. Wang, B. de Brinker, S. Stuijk, and G. de Haan, "Algorithmic Principles of Remote-PPG," IEEE Transactions on Biomedical Engineering, vol. 64, no. 7, pp.1479-1491, Jul. 2017.
[5] 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.
[6] B. F. Wu et al., "Motion Resistant Image-Photoplethysmography Based on Spectral Peak Tracking Algorithm," IEEE Access, vol. 6, pp. 21621-21634, Apr. 2018.
[7] P. Viola and M. Jones, "Rapid Object Detection Using a Boosted Cascade of Simple Features," in Proc. International Journal of Computer Vision, 2004, pp. 137-154.
[8] 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
[9] W. Chen et al. "Monitoring Body Temperature of Newborn Infants at Neonatal Intensive Care Units Using Wearable Sensors," in Proc. International Conference on Body Area Networks, 2010, pp. 188-194.
[10] C. Song et al., "Wearable Continuous Body Temperature Measurement Using Multiple Artificial Neural Networks," IEEE Transactions on Industrial Informatics, vol. 14, no. 10, pp. 4395-4406, Oct. 2018.
[11] N. Livanos et al., "Design and Interdisciplinary Simulations of a Hand-Held Device for Internal-Body Temperature Sensing Using Microwave Radiometry," IEEE Sensors Journal, vol. 18, no. 6, pp. 2421-2433, Mar. 2018.
[12] T. Tamura, Y. Maeda, M. Sekine, and M. Yoshida, "Wearable Photoplethysmographic Sensors—Past and present," Electronics, vol. 3, no. 2, pp. 282-02, Apr. 2014.
[13] Y. Freund and R. E. Schapire, "A Short Introduction to Boosting," The Japanese Society for Artificial Intelligence, vol. 14, no. 5, pp. 771–780, Sep. 1999.
[14] W. Liu et al., "SSD: Single Shot MultiBox Detector," in Proc. 2016 European Conference on Computer Vision, 2016, pp. 21-36.
[15] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," in Proc. International Conference on Learning Representations, 2015.
[16] S. Kwon, J. Kim, D. Lee, and K. Park, "ROI Analysis for Remote Photoplethysmography on Facial Video," in Proc. International Conference of the IEEE Engineering in Medicine and Biology Society, 2015, pp. 4938-4941.
[17] T. Cootes, G. Edwards, and C. Taylor, "Active Appearance Models, " IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 681-685, Jun. 2001
[18] J. F. Henriques, R. Caseiro, P. Martins, and J. Batista, "High-Speed Tracking with Kernelized Correlation Filters," in Proc. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, pp. 583-596.
[19] N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," in Proc. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 886-893, 2005.
[20] G. de Haan and V. Jeanne, "Robust Pulse Rate From Chrominance-Based rPPG," in IEEE Transactions on Biomedical Engineering, vol. 60, no. 10, pp. 2878-2886, Oct. 2013.
[21] G. A. Cavagna et al., "The Determinants of the Step Frequency in Running, Trotting and Hopping in Man and Other Vertebrates." The Journal of Physiology vol. 399, no. 10, pp. 81-92, May 1988.
[22] "U5855A TrueIR 熱影像儀," [Online]. Available: https://www.keysight.com/zh-TW/pd-2417816-pn-U5855A/trueir-thermal-imager-350c?cc=TW&lc=cht
[23] "Lwir Micro Thermal Camera Module," [Online]. Available: https://www.flir.com/products/lepton/
[24] "Emissivity Table," [Online]. Available: https://www.thermoworks.com/emissivity_table
[25] K. F. Man, K. S. Tang, and S. Kwong. "Genetic Algorithms: Concepts and Applications," IEEE Transactions on Industrial Electronics, vol. 43, no. 5, pp. 519-534, Oct. 1996.
[26] "Polar H7," [Online]. Available: https://www.polar.com/tw-zh/products/accessories/H7_heart_rate_sensor
[27] "運用CUDA開發," [Online]. Available: https://www.nvidia.com.tw/object/cuda_learn_tw_old.html