(3.235.139.152) 您好!臺灣時間:2021/05/11 12:22
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:鄭宇宏
研究生(外文):Yu-Hong Zheng
論文名稱:一個使用移動歷史紅外線影像為基礎的睡眠動作偵測系統
論文名稱(外文):A Sleep Motion Detection System Based on Infrared MHI Images
指導教授:繆紹綱繆紹綱引用關係
指導教授(外文):Shaou-Gang Miaou
學位類別:碩士
校院名稱:中原大學
系所名稱:電子工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:74
中文關鍵詞:睡眠翻身偵測居家照護睡眠品質近紅外線攝影機
外文關鍵詞:Near infrared Camera (Near-IR Camera)Sleep QualityBody Turn Detection during SleepingHome Health-Care
相關次數:
  • 被引用被引用:0
  • 點閱點閱:233
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
睡眠佔據人的一生約三分之一的時間。當夜間的睡眠品質不好時,會間接影響到日間的作息,進而使心理及生理受到損害。近年來,國內也逐漸重視睡眠品質,因而成立了許多睡眠中心,其中睡眠品質的偵測為工作重點之一,需要投入足夠的人力及精密昂貴的醫療器材,才得以維護其醫療與照護的品質。本論文提出一套以視覺為基礎,使用近紅外線攝影機且能應用於居家與醫療照護機構的睡眠行為偵測系統,希望此低成本系統能幫助醫生做後端的資料分析,迅速判斷出患者的睡眠狀況,以改善睡眠品質。
本系統分析移動歷史影像的向量,得到翻身特徵,接著透過翻身偵測及配合睡眠姿勢狀態圖的使用,進而得知當下的睡眠姿勢。另外,使用歷史移動影像的移動能量以及適合的門檻值,使得系統可以正確捕捉到一些微小動作的持續時間,提升整體睡眠品質偵測效率。
實驗結果顯示,本系統成功的解決了連續影像相減法的雜訊生成及特徵不明顯等問題,也成功偵測出睡眠姿勢。而在睡眠品質分析方面,系統分析結果頗接近實際的睡眠品質數值,因此可以證明本論文提出一個能有效偵測睡眠品質的分析系統。
One third of our life is spent in sleeping. If our sleeping quality is poor at night, it will indirectly affect our daily activities and harm our physical and psychological health. In recent years, domestic people are gradually paying attention to sleeping quality, thus a number of sleep centers are established, where monitoring sleeping quality is one of the major tasks. It requires sufficient manpower and sophisticated, expensive medical equipments to maintain certain levels of medical and health-care quality. This thesis proposes a vision-based sleeping behavior detection system using an infrared camera. The proposed low cost system can be applied to both home and health-care institutions, hoping that it can assist doctors to do data analysis and quickly determining and improving one’s sleeping quality.
The proposed system analyzes vectors of the Motion History Imaging (MHI) to get the feature of the turn of body. Then, the system uses body turn detection and a sleeping status state diagram to get the current sleep posture. In addition, with the motion energy of the MHI and a suitable threshold, the system can accurately capture the duration of some small movements and enhance the detection efficiency of overall sleeping quality.
Experimental results show that the proposed system has overcome the problem of noise creation and unobvious features of the Temporal Differencing approach for adjacent frames and has successfully detected sleep postures correctly. Finally, the result of the sleep quality analysis is close to the actual value, showing that we have proposed an effective sleep quality analyzing system.
目錄
摘要...........................................................................I
Abstract.....................................................................II
致謝.........................................................................III
目錄..........................................................................IV
圖索引.......................................................................VII
表索引.........................................................................X
第一章 緒論....................................................................1
1-1 研究動機與目的..............................................................1
1-2 相關研究...................................................................3
1-2-1 睡眠品質.................................................................3
1-2-2 移動歷史影像..............................................................6
1-3 論文架構...................................................................8
第二章 系統架構...............................................................10
2-1 近紅外線攝影機介紹.........................................................10
2-2 系統流程..................................................................12
2-3 影像處理技術...............................................................13
2-3-1 空間濾波................................................................13
2-3-2 二值化..................................................................14
2-3-3 膨脹與侵蝕...............................................................15
2-3-4 ROI區域.................................................................16
2-3-5 前景物擷取...............................................................16
第三章 特徵抽取與睡眠品質分析...................................................19
3-1 特徵抽取..................................................................19
3-1-1 移動歷史影像.............................................................19
3-1-2 方向性移動歷史影像........................................................21
3-2 睡眠行為分類...............................................................25
3-2-1 上床動作................................................................25
3-2-2 下床動作................................................................27
3-2-3 右翻身動作..............................................................28
3-2-4 左翻身動作..............................................................30
3-3 清醒/睡眠判定.............................................................31
3-4 辨識流程..................................................................32
3-4-1 睡眠品質分析.............................................................32
3-4-2 睡眠動作分類判斷法則......................................................33
3-4-3 睡眠姿勢判定.............................................................36
第四章 實驗結果與討論..........................................................37
4-1 實驗設備..................................................................37
4-2 評估方法..................................................................38
4-2-1 睡眠品質................................................................38
4-2-2 行為偵測................................................................39
4-3 睡眠品質分析..............................................................40
4-3-1 雜訊處理................................................................40
4-3-2 時間判定................................................................41
4-3-3 上床/下床動作偵測........................................................42
4-3-4 睡眠品質門檻值調整.......................................................46
4-3-5 睡眠品質分析結果.........................................................51
4-4 睡眠姿勢..................................................................52
4-4-1 無遮蔽情況..............................................................53
4-4-2 遮蔽情況................................................................55
第五章 結論與未來展望..........................................................58
5-1 結論......................................................................58
5-2 未來展望..................................................................58
參考文獻......................................................................60
作者簡介......................................................................64


圖索引
圖1 系統架構圖................................................................10
圖2 近紅外線攝影機所擷取的典型影像...............................................11
圖3實驗使用的近紅外線攝影機[29]。(a)側面圖;(b)正視圖。............................11
圖4 系統流程圖.................................................................12
圖5 3X3遮罩示意圖..............................................................13
圖6 空間濾波器之運算遮罩。(a)平滑濾波之遮罩;(b)基本高通濾波之遮罩。.................13
圖7 以門檻值二值化的示意圖......................................................14
圖8 二值化結果。(a)原始灰階影像;(b)二值化影像結果。...............................14
圖9 型態學基本運算結果。(a)原始二值化影像;(b)膨脹運算;(c)侵蝕運算。................15
圖10 ROI選取範圍。(a)近紅外線影像;(b) ROI區域;(c)ROI處理後的結果。...............16
圖11 連續影像相減法示意圖.......................................................17
圖12 前景物擷取。(a)現存影像;(b)前張影像;(c)差值影像;(d)二值化影像。.............17
圖12 (繼續)..................................................................18
圖13 移動歷史影像的展示。(a) 影像編號 : 1;(b) 影像編號 : 82;(c) 影像編號 : 165。..19
圖14 一個簡單的歷史移動影像變化示意圖,移動方向朝右下。(a)輸入影像時間點一;(b)輸入影像時間點二。......................................................................21
圖15 方向性移動歷史影像的展示...................................................21
圖16 梯度變化示意圖,相對應的梯度用箭頭表示[33]。 (a) 越接近影像中間強度越大; (b) 越接近影像左邊界強度越大。...........................................................22
圖17 方向性移動歷史影像。方向:上。(a) 影像編號 : 1;(b) 影像編號 : 82;(c) 影像編號 : 165。........................................................................24
圖18 方向性移動歷史影像。方向:下。(a) 影像編號 : 1;(b) 影像編號 : 82;(c) 影像編號 : 165。........................................................................24
圖19 方向性移動歷史影像。方向:左。(a) 影像編號 : 1;(b) 影像編號 : 82;(c) 影像編號 : 165。........................................................................25
圖20 方向性移動歷史影像。方向:右。(a) 影像編號 : 1;(b) 影像編號 : 82;(c) 影像編號 : 165。........................................................................25
圖21 上床動作。(a)原始影像;(b)移動歷史影像。....................................26
圖22 上床動作之方向性移動歷史影像。(a)上;(b)下。.................................26
圖23 上床動作之方向性移動歷史影像。(a)左;(b)右。.................................26
圖24 上床動作之方向性移動能量。(a)上;(b)下;(c)左;(c)右。........................27
圖25 下床動作。(a)原始影像;(b)移動歷史影像。.....................................27
圖26 下床動作之方向性移動歷史影像。(a)上;(b)下。.................................28
圖27 下床動作之方向性移動歷史影像。(a)左;(b)右。.................................28
圖28 下床動作之方向性移動能量。(a)上;(b)下;(c)左;(c)右。........................28
圖29 右翻身動作。(a)原始影像;(b)移動歷史影像。...................................29
圖30 右翻身動作之方向性移動歷史影像。(a)上;(b)下。...............................29
圖31 右翻身動作之方向性移動歷史影像。(a)左;(b)右。...............................29
圖32 右翻動作之方向性移動能量。(a)上;(b)下;(c)左;(d)右。.......................30
圖33 左翻身動作。(a)原始影像;(b)移動歷史影像。..................................30
圖34 左翻身動作之方向性移動歷史影像。(a)上;(b)下。...............................31
圖36 左翻動作之方向性移動能量。(a)上;(b)下;(c)左;(c)右。.......................31
圖37 清醒和睡眠判定結果圖。(a)移動歷史影像能量圖;(b)睡眠/清醒結果圖。...............32
圖38 睡眠品質之分析流程........................................................33
圖39 睡眠品質之分析流程........................................................35
圖40 睡眠姿勢之辨識狀態圖......................................................36
圖41 實驗環境架設示意圖........................................................37
圖42 連續影像差值累加之移動能量結果圖............................................40
圖43 移動歷史影像之移動能量結果圖................................................40
圖44 連續影像差值累加之(a)移動能量結果圖;(b) 睡眠清醒偵測圖;(c) 實際睡眠清醒偵測圖(不包括上床及下床動作)。............................................................41
圖45 移動歷史影像之(a)移動能量結果圖;(b)睡眠清醒偵測圖;(c) 實際睡眠清醒偵測圖(不包括上床及下床動作)。...............................................................42
圖46 實驗設計環境。(a)無遮蔽影像;(b)遮蔽影像。..................................43
圖47 無遮蔽情況下判斷上床動作之正確率............................................43
圖48 無遮蔽情況下判斷下床動作之正確率............................................44
圖49 遮蔽情況下判斷上床動作之正確率..............................................44
圖50 遮蔽情況下判斷下床動作之正確率..............................................45
圖51 連續影像相減法於不同的清醒門檻值之睡眠品質結果圖..............................48
圖52 連續影像相減法於不同的清醒門檻值之清醒動作次數正確率分析圖......................48
圖53 移動歷史影像於清醒門檻值為6之睡眠品質結果圖...................................49
圖54 移動歷史影像於清醒門檻值為6之動作次數正確率分析圖 .............................50
圖55 移動歷史影像於清醒門檻值為4及5之睡眠品質結果圖................................50
圖56 移動歷史影像於清醒門檻值為4及5之動作次數正確率分析圖...........................51
圖57 無遮蔽情況下判斷右翻身動作之正確率...........................................53
圖58 無遮蔽情況下判斷左翻身動作之正確率...........................................54
圖59 遮蔽情況下判斷右翻身動作之正確率.............................................55
圖60 遮蔽情況下判斷左翻身動作之正確率.............................................56

表索引
表1 單一型翻身行為之移動能量表現.................................................34
表2 混合型翻身行為之移動能量表現.................................................34
表3 系統使用的軟硬體規格........................................................37
表4 評估參數示意表.............................................................39
表5 無遮蔽情況下判斷上床/下床動作之評估參數.......................................46
表6 無遮蔽情況下判斷上床/下床動作之效能評估.......................................46
表7 遮蔽情況下判斷上床/下床動作之評估參數.........................................46
表8 遮蔽情況下判斷上床/下床動作之效能評估.........................................46
表9 實驗動作順序表(編號以其中一組為例)............................................47
表10 使用方法[8]之睡眠品質效能評估;系統門檻值僅為二值化門檻值。.....................52
表11 使用本系統方法之睡眠品質效能評估;下表系統門檻值表示為(衰減參數, 清醒門檻值, 二值化門檻值)。.......................................................................52
表12 使用本系統之方法與[8]之清醒動作次數正確率....................................52
表13 無遮蔽情況下判斷左/右翻身動作之評估參數......................................54
表14 無遮蔽情況下判斷左/右翻身動作之效能評估......................................55
表15 遮蔽情況下判斷左/右翻身動作之評估參數........................................56
表16 遮蔽情況下判斷左/右翻身動作之效能評估........................................57
[1]Ancoli-Israel, S., Kripke, D. F., Klauber, M. R., Mason, W. J., Fell, R., and Kaplan, O., “Periodic limb movements in sleep in community-dwelling Elderly,” Sleep, Vol. 14, pp. 496-500, 1991.
[2]行政院主計處:中華民國九十四年健康安全調查,台北,行政院主計處,民國九十五年。
[3]台灣睡眠醫學學會:2006年03月10日記者會,台中,台灣睡眠醫學學會,2006年。
[4]Cole, R. J., Kripke, D. F., Gruen, W., Mullaney, D. J., and Gillin, J. C., “Automatic sleep/wake identification from wrist activity,” Sleep, vol. 15, pp. 461-469, 1992.
[5]聯合晚報,長期照護傾向全民納保,台北,聯合晚報,2009年。
[6]Peng, Y. T., Lin, C. Y., Sun, M. T., and Landis, C. A., “Multimodality sensor system for long-term sleep quality monitoring,” IEEE Tran. on Biomedical Circuits and Systems, vol. 1, pp. 217-227, Sept. 2007.
[7]Shima, O., Yuko, O., Goyahan, Kumi, K. N., Ikuko, M., and Masako, T., “Examination of non-restrictive and non-invasive sleep evaluation technique for children using difference images,” in Proc. IEEE Int. Conf. on Engineering in Medicine and Biology Society (EMBS), pp. 3483-3487, Aug. 2008.
[8]Liao, W. H. and Yang, C. M., “Video-based activity and movement pattern analysis in overnight sleep studies,” in Proc. IEEE Int. Conf. on Pattern Recognition (ICPR), pp. 1-4, Dec. 2008.
[9]Yang, F. C., Kuo, C. H., Tsai, M. Y., and Huang, S. C., “Image-based sleep motion recognition using artificial neural networks,” in Proc. of IEEE Int. Conf. on Machine Learning and Cybernetics, vol. 5, pp. 2775-2780, Nov. 2003.
[10]Wang, C. W. and Hunter, A., “A robust pose matching algorithm for covered body analysis for sleep apnea,” in Proc. IEEE Int. Conf. on BioInformatics and BioEngineering, pp. 1-7, Oct. 2008.
[11]徐業良,老人福祉科技與遠距居家照護技術,滄海書局,2008。
[12]Kayed, K., Hesla, P. E. and Rosjo, O., “The actioculographic monitor of sleep,” Sleep, vol. 2, no. 2, pp. 253-260, 1979.
[13]Wheatley, D. W., Berme, N. and Ferguson-Pell, M. W., “A low-profile load transducer for monitoring movement,” Experimental Mechanics, vol. 20, no. 6, pp. 19-20, 1980.
[14]Nakajima, K., Osa, A., Kasaoka, S., Nakashima, K., Maekawa, T., Tamura T. and Miike H., “Detection of Physiological Parameters without Any Physical Constraints in Bed Using Sequential Image Processing” Jpn. J. Appl. Phys., 1996
[15]Choi1, B. H., Seo1, J. W., Choi1, J. M., Shin, H. B., Lee, J. Y., Jeong, D. U., and Park, K. S., “Non-constraining sleep/wake monitoring system using bed actigraphy,” Medical and Biological Engineering and Computing, vol. 45, no.1, pp. 107-114, Jan. 2007.
[16]Gordon, S., Grimmer, K., Trott, P., “Sleep position, age, gender, sleep quality and waking cervico-thoracic symptoms,” The Internet Journal of Allied Health Sciences and Practice, vol. 5, no. 1, Jan. 2007.
[17]自由時報,自行研發「睡眠衣」治好睡眠呼吸中止症,台北,自由時報,2009年。
[18]陳明輝,楊建銘,陳濘宏,阻塞型睡眠呼吸中止症患者伴隨失眠之非藥物處置:個案報告,臨床心理學刊,3卷2期,2006。
[19]Bobick, A. and Davis, J., “Real-time recognition of activity using temporal templates,” in Proc. of IEEE Workshop on Application of Computer Vision, Sarasota, Florida, pp. 39-42, Dec. 1996.
[20]Davis, J. and Bobick, A., “The representation and recognition of action using temporal templates,” MIT Media Lab, Perceptual Computing Group, Technical report: 402, 1997.
[21]Bradski, G. R. and Davids, J., “Motion segmentation and pose recognition with motion history gradients,” in Proc. of IEEE Workshop on Applications of Computer Vision, pp. 238-244, Dec. 2000.
[22]Li, L., Zeng, Q., Jiang, Y., and Xia, H., “Spatio-temporal motion segmentation and tracking under realistic condition,” in Proc. of IEEE Int. Symposium on Systems and Control in Aerospace and Astronautics, pp. 229-232, Jan. 2006.
[23]Ahad, M. A. R., Ogata, T., Tan, J. K., Kim, H. S., and Ishikawa, S., “Comparative analysis between two view-based methods: MHI and DMHI,” in Proc. IEEE Int. Conf. on Computer and Information Technology (ICCIT), pp. 1-6, Dec. 2007.
[24]Ahad, M. A. R., Ogata, T., Tan, J. K., Kim, H. S., and Ishikawa, S., “Moment-based human motion recognition from the representation of DMHI templates,” in SICE Annual Conference, pp. 578-583, Aug. 2008.
[25]Watanabe, K. and Kurita, T., “Motion recognition by higher order local auto correlation features of motion history images,” in ECSIS Symposium on Bio-inspired Learning and Intelligent Systems for Security (BLISS), pp. 51-55, Aug. 2008.
[26]Albu, A. B., Beugeling, T., Babul N. V., and Beach, C., “Analysis of irregularities in human actions with volumetric motion history images” in Proc. of IEEE Workshop on Motion and Video Computing, pp. 16-16, Feb. 2007.
[27]維基百科,紅外線,http://zh.wikipedia.org/
[28]電腦視覺監控產學研聯盟電子報,強將實業:紅外線熱像儀簡介,http://140.113.87.114/cvrc/edm/vol_4/info3.htm
[29]勝特力,KMS-D54K4 彩色風雨型日夜兩用攝影機,http://www.100y.com.tw/
[30]連國珍,數位影像處理,儒林圖書有限公司,2004。
[31]繆紹綱編譯,數位影像處理,普林斯頓國際有限公司,2003。
[32]電腦視覺監控產學研聯盟電子報,淺談影像監控之背景建立技術,http://140.113.87.114/cvrc/edm/vol_2/skill_7.htm
[33]維基百科,梯度,http://zh.wikipedia.org/
[34]Siegel, S. and Castellan, N., Nonparametric Statistics for the Behavioral Sciences, 2nd Ed., McGraw-Hill, New York, 1988.
[35]李卓偉,統計學,致勝文化事業有限公司,2000。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔