請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/46860
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 許永真(Yung-Jen Hsu) | |
dc.contributor.author | Chun-Hao Liao | en |
dc.contributor.author | 廖俊豪 | zh_TW |
dc.date.accessioned | 2021-06-15T05:42:21Z | - |
dc.date.available | 2013-08-20 | |
dc.date.copyright | 2010-08-20 | |
dc.date.issued | 2010 | |
dc.date.submitted | 2010-08-20 | |
dc.identifier.citation | [1] T. Acharya and A. Ray. Image processing: principles and applications. Wiley-
Interscience, 2005. [2] S. Basu. Conversational scene analysis. PhD thesis, 2002. [3] E. Berry, A. Hampshire, J. Rowe, S. Hodges, N. Kapur, P. Watson, G. Browne, G. Smyth, K. Wood, and A. Owen. The neural basis of e?ective memory therapy in a patient with limbic encephalitis. Journal of Neurology, Neurosurgery & Psychiatry, 80(11):1202, 2009. [4] E. Berry, N. Kapur, L. Williams, S. Hodges, P. Watson, G. Smyth, J. Srinivasan, R. Smith, B. Wilson, and K. Wood. The use of a wearable camera, SenseCam, as a pictorial diary to improve autobiographical memory in a patient with limbic encephalitis: A preliminary report. Neuropsychological Rehabilitation, 17(4):582– 601, 2007. [5] D. Biggs and M. Andrews. Acceleration of iterative image restoration algorithms. Applied Optics, 36(8):1766–1775, 1997. [6] D. Byrne, A. Doherty, C. Snoek, G. Jones, and A. Smeaton. Validating the detection of everyday concepts in visual lifelogs. In Semantic Multimedia: Third International Conference on Semantic and Digital Media Technologies, SAMT 2008, Koblenz, Germany, December 3-5, 2008. Proceedings, page 15. Springer-Verlag New York Inc, 2008. [7] N. Caprani, A. Doherty, H. Lee, A. Smeaton, N. O’Connor, and C. Gurrin. Designing 5960 BIBLIOGRAPHY a touch-screen sensecam browser to support an aging population. In Proceedings of the 28th of the international conference extended abstracts on Human factors in computing systems, pages 4291–4296. ACM, 2010. [8] S. Cha and S. Srihari. On measuring the distance between histograms. Pattern Recognition, 35(6):1355–1370, 2002. [9] Y.-C. Chang, C.-W. Hsueh, and Y.-J. Hsu. Transportation mode detection with single accelerometer on smart phones. Master’s thesis, National Taiwan University, 2010. [10] T. Choudhury, G. Borriello, S. Consolvo, D. Haehnel, B. Harrison, B. Hemingway, J. Hightower, et al. The mobile sensing platform: An embedded activity recognition system. IEEE Pervasive Computing, pages 32–41, 2008. [11] C. Conaire, N. O ’ Connor, A. Smeaton, and G. Jones. Organising a daily visual diary using multi-feature clustering. In Proc. of 19th annual Symposium on Electronic Imaging. Citeseer, 2007. [12] T. Deselaers, D. Keysers, and H. Ney. Discriminative training for object recognition using image patches. 2005. [13] T. Deselaers, D. Keysers, and H. Ney. Features for image retrieval: An experimental comparison. Information Retrieval, 11(2):77–107, 2008. [14] A. Doherty et al. Combining image descriptors to e?ectively retrieve events from visual lifelogs. In Proceeding of the 1st ACM international conference on Multimedia information retrieval, pages 10–17. ACM, 2008. [15] A. Doherty, A. Smeaton, K. Lee, and D. Ellis. Multimodal segmentation of lifelog data. RIAO 2007-Large-Scale Semantic Access to Content (Text, Image, Video and Sound), 2007. [16] G. Dork’o and C. Schmid. Object class recognition using discriminative local features. Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005. [17] R. Harper, D. Randall, N. Smythe, C. Evans, L. Heledd, and R. Moore. Thanks for the memory. In Proceedings of the 21st British HCI Group Annual ConferenceBIBLIOGRAPHY 61 on HCI 2008: People and Computers XXI: HCI... but not as we know it-Volume 2, pages 39–42. British Computer Society, 2007. [18] S. Hodges, L. Williams, E. Berry, S. Izadi, J. Srinivasan, A. Butler, G. Smyth, N. Kapur, and K. Wood. SenseCam: A retrospective memory aid. UbiComp 2006: Ubiquitous Computing, pages 177–193, 2006. [19] C. Hsu and C. Lin. A comparison of methods for multiclass support vector machines. IEEE transactions on Neural Networks, 13(2):415–425, 2002. [20] D. Huynh. Human Activity Recognition with Wearable Sensors. 2008. [21] P. Jansson and M. Richardson. Deconvolution of images and spectra. Optical Engi- neering, 36:3224, 1997. [22] F. Jurie and B. Triggs. Creating e?cient codebooks for visual recognition. In Tenth IEEE International Conference on Computer Vision, 2005. ICCV 2005, pages 604– 610, 2005. [23] M. Lawton and E. Brody. Assessment of older people: self-maintaining and instru- mental activities of daily living. The Gerontologist, 9(3 Part 1):179, 1969. [24] M. Lee and A. Dey. Lifelogging memory appliance for people with episodic mem- ory impairment. In Proceedings of the 10th international conference on Ubiquitous computing, pages 44–53. ACM, 2008. [25] J. Lester, T. Choudhury, and G. Borriello. A practical approach to recognizing physical activities. Pervasive Computing, pages 1–16, 2006. [26] S. Lindley, D. Randall, M. Glancy, N. Smyth, and R. Harper. Re?ecting on oneself and on others: Multiple perspectives via SenseCam. In CHI 2009 workshop on Designing for Re?ection on Experience. [27] S. Lindley, D. Randall, W. Sharrock, M. Glancy, N. Smyth, and R. Harper. Narra- tive, memory and practice: Tensions and choices in the use of a digital artefact. In Proceedings of the 2009 British Computer Society Conference on Human-Computer Interaction, pages 1–9. British Computer Society, 2009.62 BIBLIOGRAPHY [28] Z. Liu, Y. Wang, and T. Chen. Audio feature extraction and analysis for scene segmentation and classi?cation. The Journal of VLSI Signal Processing, 20(1):61– 79, 1998. [29] D. Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91–110, 2004. [30] D. Nguyen, G. Marcu, G. Hayes, K. Truong, J. Scott, M. Langheinrich, and C. Ro- duner. Encountering SenseCam: personal recording technologies in everyday life. In Proceedings of the 11th international conference on Ubiquitous computing, pages 165– 174. ACM, 2009. [31] R. Paredes, J. Perez-Cortes, A. Juan, and E. Vidal. Local representations and a direct voting scheme for face recognition. In Workshop on Pattern Recognition in Information Systems, pages 71–79, 2001. [32] J. Parkka, M. Ermes, P. Korpipaa, J. Mantyjarvi, J. Peltola, and I. Korhonen. Ac- tivity classi?cation using realistic data from wearable sensors. IEEE Transactions on Information Technology in Biomedicine, 10(1):119, 2006. [33] J. Russ. The image processing handbook. CRC, 2007. [34] A. Sellen, A. Fogg, M. Aitken, S. Hodges, C. Rother, and K. Wood. Do life-logging technologies support memory for the past?: an experimental study using sensecam. In Proceedings of the SIGCHI conference on Human factors in computing systems, page 90. ACM, 2007. [35] A. Smeaton. Content vs. context for multimedia semantics: the case of SenseCam image structuring. Semantic Multimedia, pages 1–10, 2006. [36] K. Tang, J. Hong, I. Smith, A. Ha, and L. Satpathy. Memory karaoke: using a location-aware mobile reminiscence tool to support aging in place. In Proceedings of the 9th international conference on Human computer interaction with mobile devices and services, pages 305–312. ACM, 2007. [37] H. Tong, M. Li, H. Zhang, and C. Zhang. Blur detection for digital images usingBIBLIOGRAPHY 63 wavelet transform. In 2004 IEEE International Conference on Multimedia and Expo, 2004. ICME’04, pages 17–20, 2004. [38] S. Vemuri, C. Schmandt, and W. Bender. iRemember: a personal, long-term memory prosthesis. In Proceedings of the 3rd ACM workshop on Continuous archival and retrival of personal experences, page 74. ACM, 2006. [39] P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume 1. Citeseer, 2001. [40] P. Wilson and J. Fernandez. Facial feature detection using Haar classi?ers. Journal of Computing Sciences in Colleges, 21(4):133, 2006. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/46860 | - |
dc.description.abstract | 我們利用手機上的照相機,錄音機以及三軸加速器,結合 SenseCam 的特性而發明一個手機的新應用,我們稱之為 SenseMobile 。 SenseMobile 結合影像,聲音,以及加速度值來建立日常生活活動辨識系統。然而,其他可攜帶型的裝置卻僅僅是辨識一些基本的身體活動,而不是較進階的日常生活活動 (ADLs) ,但在本論文裡,我們萃取實用的特徵值來辨識日常生活活動。
在影像特徵萃取裡,經過影像前處理再取得影像裡的人臉資訊,以及建立局部影像分類系統;而在聲音特徵擷取裡,我們從時間領域,抓取音量、非靜音率、以及辨識人聲的最大峰值,波峰數量,而從頻率領域裡,萃取語音辨識裡常用的梅爾倒頻係數;最後,我們先分類加速值的分佈情形,計算不同分佈占的比例來得到加速度的特徵值。在方法上,我們利用 sliding window 方式進行特徵值取樣,再利用機器學習的數學模型進行辨識。 本論文裡,我們設計兩種實驗:實驗環境裡以及真實環境裡的日常生活活動辨識,在多種活動辨識上,比較 (Support Vector Machine)SVM 和 (Hidden Markov Model)HMM 的精準度,也比較影像,聲音、加速度的特徵值對於多種活動辨識的精準度之優劣,另外在單一活動辨識上,我們針對個別活動分別執行最佳化來提昇活動辨識的精準度。而從這兩種實驗結果證明我們在日常生活活動辨識的成功以及提出需要改進的部份。 | zh_TW |
dc.description.abstract | We combine the camera, the sound recorder, and the accelerometer on the smart-phone with the machanism of SenseCam to invent a new application of smartphones called as SenseMobile. SenseMobile employs images, sounds and accelerometer values to build an activities of daily living(ADLs) recognition system. However other portable devices merely recognize physical activities instead of high-level activities. In this thesis, we extract effective features to implementing activity recognition. In image feature extraction, we detect human face and cluster local images after pre-processing. For sound feature extraction, in the time domain, we extract volume, non-silent ratio and two human voice features - maximum peak value and number of peaks. Furthermore, From the frequency domain, we extract Mel-frequency cepstral coefficients (MFCCs), which are popular in speech recognition. After clustering vibration types, we calculate probabilities of types in accelerometer feature extraction. Then we sample instances on sliding time window and implement classification on machine learning models.
We design two experiments - ADLs recognition in experimental environment and in real environment. In multiple classifications, we compare accuracy from Support Vector Machine(SVM) and Hidden Markov Model(HMM) models, and from distinct data types. In binary classifications, we utilize one-against-all method and optimize individual activity recognition. Eventually, results of two experiments prove success in ADLs recognition and bring forward unsolved defects of SenseMobile. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T05:42:21Z (GMT). No. of bitstreams: 1 ntu-99-R97922109-1.pdf: 9922059 bytes, checksum: e948a4b56c785d3c70a1727266105dd9 (MD5) Previous issue date: 2010 | en |
dc.description.tableofcontents | Abstract i
List of Figures vii List of Tables ix Chapter 1 Introduction 1 1.1 Motivation ................................. 1 1.2 Design Consideration ........................... 2 1.3 Research Objective & Thesis Organization ............... 5 Chapter 2 Related Work 6 2.1 Lifelogging ................................. 6 2.1.1 SenseCam ............................. 6 2.1.2 Other Devices ........................... 8 2.2 Activity Recognition on Wearable Device ................ 8 2.2.1 Physical Activity Recognition .................. 8 2.2.2 High-Level Activity ........................ 10 ivChapter 3 Feature Extraction 12 3.1 Image ................................... 12 3.1.1 Pre-processing .......................... 14 3.1.2 Image Feature Extraction .................... 20 3.2 Sound ................................... 23 3.2.1 Time Domain ........................... 23 3.2.2 Frequency Domain ........................ 25 3.3 Accelerometer ............................... 25 Chapter 4 Methodology 26 4.1 Feature Re-sampling ........................... 26 4.2 Machine Learning models ........................ 27 Chapter 5 Experiment I 29 5.1 Experimental Setup ............................ 29 5.1.1 Experimental Environment ................... 29 5.1.2 Experimental Process ...................... 32 5.2 Dataset .................................. 33 5.3 Evaluation & Conclusion ......................... 33 5.3.1 Decision on K Image , K Accel .................... 35 5.3.2 Decision on Time Window Size ................. 35 5.3.3 Distinct Classi?ers ........................ 36 5.3.4 Recognizing each Activity .................... 37 5.3.5 Distinct Combinations of Data Types in Recognizing each Activity .............................. 38 v5.3.6 Individual Activity Recognition ................. 42 Chapter 6 Experiment II 45 6.1 Experimental Setup ............................ 45 6.1.1 Experimental Process ...................... 45 6.2 Dataset .................................. 46 6.3 Evaluation & Conclusion ......................... 46 6.3.1 Decision on K Image , K Accel .................... 48 6.3.2 Decision on Time Window Size ................. 48 6.3.3 Distinct Classi?ers ........................ 49 6.3.4 Recognizing each Activity .................... 50 6.3.5 Distinct Combinations of Data Types in Recognizing each Activity .............................. 52 6.3.6 Individual Activity Recognition ................. 53 Chapter 7 Conclusion 55 7.1 Summary in Experiments ........................ 55 7.1.1 Comparison in experiments ................... 55 7.1.2 Common Points in Experiments ................. 56 7.2 Summary of Work ............................ 57 7.3 Summary of Contribution ........................ 57 7.4 Limitation of SenseMobile ........................ 58 Bibliography 59 | |
dc.language.iso | en | |
dc.title | 智慧型手機建構日常生活活動模型與辨識系統之研究 | zh_TW |
dc.title | Modeling and Recognition of Activities of Daily Living | en |
dc.type | Thesis | |
dc.date.schoolyear | 98-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 陳彥仰(Yen-Yang Chen),陳俊良(Chuen-Liang Chen),王傑智(Chieh-Chih Wang),林光龍(Kuang-Lung Lin) | |
dc.subject.keyword | 影像特徵擷取,聲音特徵擷取,加速度特徵擷取,日常生活活動辨識, | zh_TW |
dc.subject.keyword | image,sound and accelerometer feature extraction,ADLs recognition, | en |
dc.relation.page | 63 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2010-08-20 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-99-1.pdf 目前未授權公開取用 | 9.69 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。