隨著社會進步和醫學發達，國人的平均壽命日益增長，台灣老年人口的比例正逐年上升。如何利用目前的科技來改善老年人的日常生活以及健康照護是很重要的議題。隨著老年人口越來越多，老年人照護的需求也隨之增加，照護中心也跟著逐年設立。有些照護中心會裝視訊監控系統監看老年人的日常生活以及保障老年人生命安全。然而，通常這樣的監控系統，都必須要有一個人長時間的察看監視器，才不會遺漏意外事情的發生。這是一個沉重的負擔，但卻是一件不可避免的事情。除此之外，老年人的健康狀況也是照護中心很關心的，以老年人健康照護而言，睡眠障礙是一種很常見的症狀，醫護人員在夜間都會定時巡視老年人的房間，了解老年人的睡眠狀況。然而，在醫護人員沒有巡房的時間，老年人亦可能會有上下床或進出房間的行為，而沒有被醫護人員察覺。
因此，為了改善上述的情形以及更精確地掌握老年人的睡眠狀況，本論文提出一個基於熱感影像之睡眠評估系統，透過熱感攝影機的拍攝，偵測老年人在房間中上下床的行為，計算老年人在夜間的臥床時間以及上下床的次數，輔助醫護人員評估老年人的睡眠狀況。藉此，不僅可以幫助照護中心的醫護人員瞭解老年人每日的睡眠狀況，亦可減緩他/她們在夜間巡房的負擔，更可以作為日後醫生診斷用藥的輔助資訊。最後經實驗結果顯示，本論文提出的演算法在偵測老年人上下床的行為上可達到90%的準確率。

With social progress and medical development, the dramatic increase in average life expectancy is growing and the proportion of the elderly in Taiwan is increasing year by year. How to use start-of-art technology to improve the elderly’s daily life has become an important issue. With an aging population growing, the demand for nursing centers of the elderly has increased and nursing centers have been set up year after year. In order to avoid accidents, some of nursing centers would install cameras for monitoring the elderly’s conditions. However, it is necessary to keeps a person watching the screens all the time, which is a hung human burden. furthermore, sleeping plays a vital role in good health and well-being throughout elderly’s life. In order to understand the sleep of an elderly, caregivers have to spend their time checking the room regularly. Meanwhile, the intermittent between checking also become as a safety dead zone period.
Hence, this paper presents a scheduled-based hotspot detection to detect activities of an elderly in the night, including going to bed and getting out of bed and develop a thermal image based sleep summarization system to automatically record detected results. The detected results could help caregivers not only understand the sleep situation of the elderly but also reduce their burden. Moreover, doctors could consider the information of our system when they prescribe medicines for the elderly. The experimental show that the proposed algorithms have satisfied detecting rate for the defined activities.

Reference
[1] 《中華民國2012年至2060年人口估計報告》，行政院經濟建設委員會
http://iknow.stpi.narl.org.tw/Post/Files/policy/2012/policy_12_037_2.pdf
[2] 105年第3週內政統計通告(104年底人口結構分析)，內政部統計處 http://www.moi.gov.tw/stat/news_content.aspx?sn=10225
[3] 郭代璜、蘇貞英，《銀髮族幸福照護》，科學發展第509期，2015年5月。
http://ejournal.stpi.narl.org.tw/NSC_INDEX/Journal/EJ0001/10405/10405-07.pdf
[4] 曾銀貞、廖玟君、曾月霞，社區老人睡眠品質及其相關因素探討，中山醫學大學護理學系
[5] D. L. Wingard and L. F. Berkman, “Mortality risk associated with sleeping patterns among adults”, Sleep, 6(2), 102-107,1983.
[6] D. Zhou, M. Dillon, “Tracking-based deer vehicle collision detection using thermal image”, In: IEEE International Conference on Robotics and Biomimetics, 2009
[7] B. C. Arrue, A. Ollero, J.R. Matinez de Dios, “An intelligent system for false alarm reduction in infrared forest-fire detection.”, IEEE Intell. Syst. Appl. 15(3), 64–73,2000.
[8] E. Ohel, S.R. Rotman, D.G. Blumberg ,L. Sagiv, “Anomaly gas remote sensing and tracking using a field-portable imaging thermal radiometric spectrometer”, In: IEEE 24th Convention of Electrical and Electronics Engineers in Israel, 2006.
[9] W. Wang, J. Zhang, C. Shen, “Improved human detection and classification in thermal images”, In: 17th IEEE International Conference on Image Processing, 2010.
[10] J. A. Jang, G. J. Seo,Y., J. S. Park, “Performance improvement of human detection using thermal imaging cameras based on mahalanobis distance and edge orientation histogram”, In: Information Technology Convergence, Lecture Notes in Electrical Engineering, vol. 253, pp. 817–825, 2013
[11] V. John, Z. Liu, S. Mita and B. Qi, “Pedestrian Detection in Thermal Images Using Adaptive Fuzzy C-Means Clustering and Convolutional Neural Networks”, 14th IAPR International Conference on Machine Vision Applications (MVA),2015.
[12] J. F. Head, R. L. Elliott, “Infrared Imaging: Making Progress in Fulfilling Its Medical Promise.”, IEEE Engineering in Medicine and Biology, vol. 21, Issue 6, pp. 80-85, 2002.
[13] B. L. ahiri, S. Bagavathiappan, T. Jayakumar, J. Philip,”Medical applications of infrared thermography: a review. Infrared Phys”, Technol. 55(4), 221–235, 2012
[14] G. C. Wishart, M. Campisi, M. Boswell, D. Chapman, V. Shackleton, S. Iddles, A Hallett, P.D. Britton, “The accuracy of digital infrared imaging for breast cancer detection in women undergoing breast biopsy”, European Journal of Surgical Oncology 36 535–540, 2010.
[15] L. Vilcahuaman, R. Harba, R. Canals, M. Zequera, C. Wilches, M.T. Arista, L. Torres and H. Arbañil, “Detection of Diabetic Foot Hyperthermia by Infrared Imaging”, Engineering in Medicine and Biology Society(EMBC), 2014.
[16] M. K. Bhowmik, D. Bhattacharjee, M. Nasipuri, D. K. Basu, M. Kundu,” Classification of polar-thermal eigenfaces using multilayer perceptron for human face recognition”, In: IEEE Region 10 and the Third international Conference on Industrial and, Information Systems, 2008.
[17] A. Guzman, M. Goryawala , M. Adjouadi , ”Generating thermal facial signatures using thermal infrared image”, In: IEEE International Conference on Emerging Signal Processing Applications, 2012.
[18] A. M. Guzman, M. Goryawala, J.Wang, A. Barreto, J. Andrian, N. Rishe, M. Adjouadi, “Thermal imaging as a biometrics approach to facial signature authentication”, IEEE J. Biomed. Health Inf. 17(1), 214–222 ,2013
[19] B. A. Rajoub, and R. Zwiggelaar, “Thermal Facial Analysis for Deception Detection”, IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, VOL. 9, NO. 6, 2014.
[20] D. Guan, T. Ma, W. Yuan and Y. Lee, “Review of Sensor-based Activity Recognition Systems”, IEEE Technical Review, vol.28, no. 5, p. 418, 2011.
[21] K. Kim., T. H. Chalidabhongse, D. Harwood and L. Davis, “Real-time foreground-background segmentation using codebook model”, Real-Time Imaging, vol.11, no.3, pp.172-185, 2005.
[22] O. Barnich and M. Van Droogenbroeck, “ViBe: A universal background subtraction algorithm for video sequences”, IEEE Transactions on Image Processing, vol.20, no.6, pp.1709-1724, 2011.
[23] B. K. P. Horn and B. G. Schunck, “Determining optical flow”, Artificial Intellignece, vol.17, pp. 185-203, 1981.
[24] R. Poppe, “A survey on vision-based human action recognition”, Image and Vision Vision Computing, vol.28, no.6, pp.976-990, 2010.
[25] V. Sarvesh, A. Anupam, “A survey on activity recognition and behavior understanding in video surveillance”, “The Visual Computer”, vol.29, no.10, pp.983-1009, 2013.
[26] F. Aaron Bobick, James W. Davis, “The recognition of human movement using temporal templates”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.23, no.3, pp.257-267, 2001.
[27] M. A. R. Ahad, J.K. Tan, H. S. Kim and S. Ishikawa, “Motion history image: its variants and application”, Machine Vision and Applications, vol.23, no.2, pp. 255-281, 2012.
[28] S. M. A. Masudul, T. J. Kooi, K. Hyoungseop and I. Seiji, “Recognizing Human Actions using Histogram of Local Binary Patterns”, International Symposium on System Integration, pp.54-59, 2013.
[29] H. Ju and B. Bir , ”Human Activity Recognition in Thermal Infrared Imagery”, Conference on Computer Vision and Pattern Recognition, vol.3 pp.17, 2005.
[30] L. Ivan and L. Tony, ”Space-time Interest Points” , Proceedings of the International Conference on Computer Vision(ICCV), vol.1 pp.432-439, 2003.
[31] J. Shuiwang, X. Wei and Y. Ming, ”3D convolutional Neural Networks for Human Action Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.35, no.1 pp.221-231, 2013.
[32] B. Moez, M. Frank, W. Christian, G. Christophe and B. Atilla ,” Sequential Deep Learning for Human Action Recognition”, International Workshop on Human Behavior Understanding, pp.29-39, 2011.
[33] W. Yang, Y. Wang and G. Mori, “Recognizing human actions from still images with latent poses”, In Proc. 2010 IEEE Conf. on Computer Vision and Pattern Recognition, pp.2030-2037, 2010.
[34] Q. Huimin, M. Yaobin, X. Wenbo and W. Zhiquan, “Recognition of human activities using SVM multi-class classifier”, Pattern Recognition Letters, vol.31, no.2, pp.100-111, 2010
[35] Y. Du, W. Wang and L. Wang, “Hierarchical recurrent neural network for skeleton based action recognition”, In: CVPR, 2015.
[36] R. Vezzani, M. Piccardi and R. Currhiara, ” HMM based action recognition with projection histogram features”, In ICPR pp.286-293, 2010
[37] C. D. Liu, Y. N. Chung and P. C. Chung, “An interaction-embedded HMM framework for human behavior understanding: With nursing environments as examples”, IEEE trans. Inf. Technol. Biomed., vol. 14, no. 5, pp. 1236-1246, 2010.
[38] L. Zhang, L. Zhange, D. Tao and B. Du, “A sparse and discriminative tensor to vector projection for human gait feature representation”, Signal Processing, vol.106, pp.245-252, 2015.
[39] I. Haritaoglu, D. Harwood and L.S. David, ”W4 Real-Time Surveillance of People and Their Activities”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no.8, 2000.