請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/31765
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 洪一平(Yi-Ping Hung) | |
dc.contributor.author | Ying-Chung Chen | en |
dc.contributor.author | 陳瀅中 | zh_TW |
dc.date.accessioned | 2021-06-13T03:19:36Z | - |
dc.date.available | 2006-07-31 | |
dc.date.copyright | 2006-07-31 | |
dc.date.issued | 2006 | |
dc.date.submitted | 2006-07-27 | |
dc.identifier.citation | [1] Y. Sheikh and M. Shah, “Exploring the space of an action for human action recognition,”
in Tenth IEEE International Conference on Computer Vision, 2005. [2] C. S. Myers and L. R. Rabiner, “A comparative study of several dynamic timewarping algorithms for connected word recognition.” in The Bell System Technical Journal, September 1981. [3] O. Boiman and M. Irani, “Detecting irregularities in images and in video.” in Tenth IEEE International Conference on Computer Vision , 2005. [4] C. Sminchisescu, A. Kanaujia, Z. Li, and D. N. Metaxas, “Conditional random fields for contextual human motion recognition.” in ICCV, 2005, pp. 1808–1815. [5] X. Lan and D. P. Huttenlocher, “Beyond trees: Common-factor models for 2d human pose recovery.” in Tenth IEEE International Conference on Computer Vision, 2005, pp. 470–477. [6] S.B.Wang, A.Quattoni, L.P.Morency, D.Demirdjian, and T.Darrel, “Hidden conditional random fields for gesture recognition.” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition , 2006. [7] J. W. Davis and A. F. Bobick, “The representation and rocognition of action using temporal templates.” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997. [8] C. Schuldt, I. Laptev, and B. Caputo, “Recognizing human actions: A local svm approach,” in International Conference on Pattern Recognition, 2004. [9] I. Laptev and T. Lindeberg, “Space-time interest points.” in Tenth IEEE Interna- tional Conference on Computer Vision, 2003. [10] Y. Ke, R. Sukthankar, and M. Hebert, “Efficient visual event detection using volumetric features,” in Tenth IEEE International Conference on Computer Vision, October 2005. [11] 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 , 2001. [12] A. Yilmaz and M. Shah, “Actions as objects: A novel action representation.” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. [13] C. Rao and M. Shah, “View-invariance in action recognition.” in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001. [14] R. Kjeldesn and J. Kender, “Finding skin in color images.” in Int workshop on Automatic face and gesture recogn, 1996. [15] V. Parameswaran and R. Chellappa, “View invariance for human action recognition.” in International Journal of Computer Vision , 2006. [16] Rothwell, “Object recognition through invariant indering.” in Oxford Science Pub- lications, 1995. [17] V. Guruswami and A. Sahai, “Multiclass learning, boosting, and error-correcting codes.” in Proceedings of the twelfth annual conference on Computational learning theory, 1999. [18] C. Stauffer and W. Grimson, “Adaptive background mixture models for real-time tracking.” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998. [19] S. Belongie, J. Malik, and J. Puzicha, “Shape matching and object recognition using shape contexts,” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition , 2001. [20] 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 , 2001. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/31765 | - |
dc.description.abstract | 在這篇論文中,我們綜合了體積特徵(volumetric feature)還有空間與時間校正(spatio-temporal alignment)來處理動作識別這個問題。我們使用了適性背景混和模型(adaptive background mixture model)來將人體的部份從影片之中擷取出來,將他們正規化之後依據人體的重心把他們放在每張影格中央。接下來,我們使用了動態時間翹曲(Dynamic Time Warping)配合形狀內容(Shape Context)來作影片方面的時間校正。作完空間與時間校正之後,我們從這段包含著動作的影片中擷取體積特徵來描述表演者的動作。其中體積特徵是由二維空間中的物體偵測裡頭所使用的特徵得到靈感的。為了將二元分類法應用在多類別的問題上,我們在AdaBoost上使用了錯誤更正碼來達到多類別的目的。相對於直觀上每個類別學一個分類器的方法,我們在實驗中證明了這種多類別的學習正確率並不會低於前者。在實驗中我們也闡述這種空間與時間的校正相較於沒校正前,可以大幅提昇辨識率。 | zh_TW |
dc.description.abstract | In this thesis we use volumetric feature combined with spatial and temporal alignment to deal with action recognition problem. We use the adaptive background mixture model to extract the human body out of the image sequence, normalize and align them in the center of the frame according to the centroid of figure. After that we use Dynamic Time Warping to achieve the temporal alignment, by using of a simplified version of Shape Context. Then we apply the volumetric feature inspired by 2D rectangle feature in object detection on static images. To solve the multi-class learning problem, we apply an multi-class approach of Adaboost by using error-correcting code, which is more effective than one-against-all approach. In the experiment, we demonstrate the using of spatial and temporal alignment can avoid the time-scale and space-scale issue thus improve the accuracy rate. | en |
dc.description.provenance | Made available in DSpace on 2021-06-13T03:19:36Z (GMT). No. of bitstreams: 1 ntu-95-R93944003-1.pdf: 607673 bytes, checksum: 9e7a19e131b2b1b3c15f0a07467d6796 (MD5) Previous issue date: 2006 | en |
dc.description.tableofcontents | 1 Introduction 1
1.1 Problem definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Previous work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.2.1 Model based approach . . . . . . . . . . . . . . . . . . . . . . . . 3 1.2.2 Appearance based approach . . . . . . . . . . . . . . . . . . . . . 3 1.2.3 Trajectory based approach . . . . . . . . . . . . . . . . . . . . . . 4 1.3 The approach in this thesis . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2 Features 6 2.1 Foreground Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.1.1 The background model . . . . . . . . . . . . . . . . . . . . . . . . 6 2.1.2 Foreground alignment . . . . . . . . . . . . . . . . . . . . . . . . 8 2.2 Temporal Alignment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.2.1 Dynamic Time Warping . . . . . . . . . . . . . . . . . . . . . . . 9 2.2.2 Shape Context . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.3 Volumetric Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3 Learning the classifier 14 3.1 Error-Correcting Codes . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.1.1 Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.1.2 Hadamard-matrix codes . . . . . . . . . . . . . . . . . . . . . . . 15 3.2 Multiclass Boosting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4 Experiments 18 4.1 the Database . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.2 Evaluation results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 5 Conclusion and Future work 22 Bibliography 23 | |
dc.language.iso | en | |
dc.title | 基於多類別提昇的動作識別 | zh_TW |
dc.title | Action Recognition Using Multi-class Boosting | en |
dc.type | Thesis | |
dc.date.schoolyear | 94-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 劉庭祿(Tyng-Luh Liu) | |
dc.contributor.oralexamcommittee | 傅楸善(Chiou-Shann Fuh),莊仁輝(Jen-Hui Chuang),鮑興國(Hsing-Kuo Kenneth Pao) | |
dc.subject.keyword | AdaBoost,錯誤稱正碼,動作,識別,體積特徵, | zh_TW |
dc.subject.keyword | AdaBoost,Error-correct code,action,recognition,Volumetric feature, | en |
dc.relation.page | 25 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2006-07-30 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-95-1.pdf 目前未授權公開取用 | 593.43 kB | 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。