請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/48033
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 吳家麟(Ja-Ling Wu) | |
dc.contributor.author | Hung-Wei Lin | en |
dc.contributor.author | 林弘偉 | zh_TW |
dc.date.accessioned | 2021-06-15T06:44:49Z | - |
dc.date.available | 2013-07-07 | |
dc.date.copyright | 2011-07-07 | |
dc.date.issued | 2011 | |
dc.date.submitted | 2011-06-29 | |
dc.identifier.citation | [1] A. F. Bobick and J. 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.
[2] M. K. Hu, “Visual Pattern Recognition by Moment Invariants,” IRE Transactions on Information Theory, Vol. 8, No. 2, pp. 179-187, 1962. [3] X. Zou and B. Bhanu, “Human Activity Classification Based on Gait Energy Image and Co-evolutionary Genetic Programming,” The 18th International Conference on Pattern Recognition, Vol. 3. pp. 556-559, 2006. [4] J. Han and B. Bhanu, “Individual Recognition Using Gait Energy Image,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No. 2, pp. 316-322, 2006. [5] N. M. Oliver, B. Rosario, and A. P. Pentland, “A Bayesian Computer Vision System for Modeling Human Interactions,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 8, pp. 831-843, 2000. [6] S. Rosales and S. Sclaroff, “3D Trajectory Recovery for Tracking Multiple Objects and Trajectory Guided Recognition of Actions,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2. Pp. 637-663, 1999. [7] J. W. Hsieh, Y. T. Hsu, H. Y. Liao, and C. C. Chen, “Video-Based Human Movement Analysis and Its Application to Surveillance Systems,” IEEE Transactions on Multimedia, Vol. 10, No. 3, pp. 372-384, 2008. [8] J. Lu and Y. P. Tan, “Gait-Based Human Age Estimation,” International Conference on Acoustics, Speech and Signal Processing, Vol. 5, Issue 4, pp. 761-770, 2010. [9] P. C. Chang, M. C. Tien, J. L. Wu, and C. S. Hu, “Real-time Gender Classification from Human Gait for Arbitrary View Angles,” 11th IEEE International Symposium on Multimedia, 2009. ISM ’09. PP. 88-95, 2009. [10] J. Wright, Y. Ma, Y. Tao, Z. Lin, and H. Y. Shum, “Classification via Minimum Incremental Coding Length (MICL),” SIAM Journal on Imaging Sciences, Vol. 2, No. 2, pp. 367-395, 2009. [11] EM Photonics. 2011. CULA Library R11. http://www.culatools.com/ [12] NVIDIA Corporation. 2010. CUDA toolkit 3.2. http://developer.nvidia.com/cuda-toolkit-32-downloads [13] Precision and Recall: http://en.wikipedia.org/wiki/Precision_and_recall [14] LibSVM: http://www.csie.ntu.edu.tw/~cjlin/libsvm/ [15] K-Nearest Neighbor: http://note.sonots.com/SciSoftware/knn.html#lf488b13 [16] The Weizmann dataset: http://www.wisdom.Weizmann.ac.il/~vision/SpaceTimeActions.html [17] M. Blank, L. Gorelick, E. Shechtman, M. Irani, and R. Basri, “Actions as Space-Time Shapes,” Proc. Int’l Conf. Computer Vision, pp. 1395-1402, 2005. [18] L. Gorelick, M. Blank, E. Schechtman, R. Basri, and M. Irani, “Actions as Space-Time Shapes”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No. 12, pp. 2247-2253, 2007. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/48033 | - |
dc.description.abstract | 在本篇論文中,我們提出了一個利用人類步態資訊以及最低增量編碼長度分析人類行為的方法。作為特徵,步態能量圖 (Gait Energy Image) 被轉換為向量,我們利用最低增量編碼長度分析這些步態資訊。除此之外,我們也引入對同一動作的多角度分析,以多數決的方式更進一步增進整體分析的表現。實驗結果顯示這個方法在人類行為辨識應用上的準確率平均約高達百分之九十五,除此之外,藉由圖形運算器 (GPU) 技術的協助,我們可以在很短的時間之內完成前述人類行為的分析與辨識。換言之,本文所提出的方法可以作為一個實用的模組,被整合到偵測不尋常動作的監視器系統之中。 | zh_TW |
dc.description.abstract | In this thesis, we present a novel approach based on the gait energy image (GEI) and the minimum incremental coding length (MICL) for classifying human actions. GEIs are transformed into vectors as input features, and MICL is employed to be the classifier. Moreover, the strategy of majority voting is applied to the MICL classification results to improve the overall system performance. Experimental results show that the proposed approach can achieve approximately 95% of precision, and the classification task can be accomplished in a very short time with the aid of GPU. In other words, the proposed approach can be integrated as a useful component for detecting abnormal events in video surveillance applications. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T06:44:49Z (GMT). No. of bitstreams: 1 ntu-100-R98922025-1.pdf: 3104214 bytes, checksum: 777c8d8f03a79c58b1ecd2ca09ebd403 (MD5) Previous issue date: 2011 | en |
dc.description.tableofcontents | 誌謝 i
中文摘要 ii Abstract iii 目 錄 iv 圖目錄 v 表目錄 vi Chapter 1 Introduction 1 1.1 MOTIVATION 1 1.2 RELATED WORK 2 1.2.1 Event Detection Based on Different Features 2 1.2.1.1 Shape / Contour Based Approach 2 1.2.1.2 Trajectory Based Approach 3 1.2.1.3 Skeleton Based Approach 3 1.2.2 Research Topics Based on GEIs 3 1.3 THESIS OVERVIEW AND SUMMARY OF CONTRIBUTIONS 4 Chapter 2 Gait Energy Image 6 2.1 GAIT ENERGY IMAGE (GEI) 6 2.2 NORMALIZATION AND ALIGNMENT OF GEIS 8 Chapter 3 Minimum Incremental Coding Length 18 3.1 MINIMUM INCREMENTAL CODING LENGTH (MICL) 18 3.2 SPEED UP FOR MICL 22 Chapter 4 The Voting Strategy 26 Chapter 5 The Proposed GEI-based Human Action Recognition System 29 Chapter 6 Experimental Results 31 6.1 INPUT DATA AND EXPERIMENTAL SETTINGS 31 6.2 PERFORMANCE EVALUATION 32 6.2.1 Improvement by Normalized GEI 32 6.2.2 The Voting Strategy 35 6.2.3 The Effect of Different GEI Sizes 38 6.2.4 Speed Up for MICL 41 6.2.5 Comparison with Other Classification Methods 43 6.2.6 Classification Results with Other Action Dataset 44 Chapter 7 Conclusion 47 References 49 | |
dc.language.iso | en | |
dc.title | 以加速後最低增量編碼長度分類器分析人類步態資訊之行為辨識 | zh_TW |
dc.title | Gait-Based Action Recognition via Accelerated Minimum Incremental Coding Length Classifier | en |
dc.type | Thesis | |
dc.date.schoolyear | 99-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 朱威達(Wei-Ta Chu),鄭文皇(Wen-Huang Cheng),黃俊翔(Chun-Hsiang Huang) | |
dc.subject.keyword | 行為辨識,人類步態,步態能量圖,最低增量編碼長度,圖形運算器,視覺監視系統, | zh_TW |
dc.subject.keyword | Action Recognition,Human Gait,GEI (Gait Energy Image),MICL (Minimum Incremental Coding Length),GPU,Visual Surveillance, | en |
dc.relation.page | 50 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2011-06-29 | |
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-100-1.pdf 目前未授權公開取用 | 3.03 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。