跳到主要內容

臺灣博碩士論文加值系統

(18.97.9.169) 您好!臺灣時間:2025/02/18 22:02
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

: 
twitterline
研究生:潘品忠
研究生(外文):Pan, Pin-Zhong
論文名稱:利用隨機森林之人體動作辨識技術
論文名稱(外文):Human Action Recognition using Random Forest
指導教授:黃仲陵黃仲陵引用關係鐘太郎
指導教授(外文):Huang, Chung-LinJong, Tai-Lang
學位類別:碩士
校院名稱:國立清華大學
系所名稱:電機工程學系
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:2013
畢業學年度:102
語文別:英文
論文頁數:38
中文關鍵詞:密集軌跡字樹字袋隨機森林
外文關鍵詞:Dense Trajectoriesvocabulary treeBag of wordsRandom forest
相關次數:
  • 被引用被引用:0
  • 點閱點閱:313
  • 評分評分:
  • 下載下載:43
  • 收藏至我的研究室書目清單書目收藏:0
由於人體動作辨識廣泛的應用,其在電腦視覺研究中一直是許多研究者相當感興趣的主題,其應用包含:人機互動,智慧型家庭,老年、幼年看護或是視覺監控系統;動作辨識技術在這些領域皆有很大的發展空間。先前的研究多數主要在辨識動作間差異性大的影片,但生活中有許多動作其間的差異性並不大,因此,本論文旨在提出一個辨識方法來辨識這兩種類型的動作。
對於動作辨識而言,從動作影片擷取有辨識度的特徵描述對辨識結果有很大的影響,而local features在辨識上有不錯的效能,因此本論文使用Dense Trajectories的方式來截取動作影片中motion的資訊,因Dense Trajectories可追蹤較完整的前景物件,我們根據這些trajectories將影片切割出許多spatio-temporal grid,再利用HOG及HOF來描述影像前景的appearance及motion,然後使用Bag of words來整理它們。為達更好的效果,我們使用vocabulary tree來做words的分類,進而產生放入分類器做訓練的特徵向量。本論文在分類器選擇的是採用multi-channel 的Random forest,將特徵向量中較為重要的bin利用隨機訓練的方式找出並記錄下來,來當作節點的分類函式。在測試的過程中,可經由一層層的分類來得到測試影片會落入的葉點,並根據葉點中的機率分佈來判斷此動作影片的動作型態。
我們利用兩個資料庫來驗證所提出來的方法,KTH database and URADL database。由實驗結果來看,我們的實驗結果相對於其他的方法有著較高的辨識率,也說明所提出方法可處理動作間差異性大與差異性小的影片。

Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Related work 1
1.3 System overview 4
1.4 Organization 5
Chapter 2 Feature extraction 6
2.1 Dense sampling 6
2.2 Dense trajectories 8
2.3 Trajectory-aligned descriptors 10
2.3.1 Histograms of Oriented Gradients 11
2.3.2 Histograms of Optical Flow 14
Chapter 3 Video Representation 17
3.1 Bag of Words 17
3.2 Vocabulary Tree 18
Chapter 4 Random Forest 22
4.1 Decision Tree 22
4.2 Training process of Random Forest 23
4.3 Testing of Random Forest 26

Chapter 5 Experimental Results 28
5.1 Databases 28
5.1.1 KTH database 28
5.1.2 URADL database 29
5.2 Results and Comparison 31
Chapter 6 Conclusion 35
References 36

[1] B. Ni, G. Wang and P. Moulin, "RGBD-HuDaAct: A color-depth video database for human daily activity recognition," in Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on, 6-13 Nov. 2011.
[2] P. Dollar, V. Rabaud, G. Cottrell and S. Belongie, "Behavior recognition via sparse spatio-temporal features," in Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005. 2nd Joint IEEE International Workshop on, 15-16 Oct. 2005.
[3] M. Uddin, N. D. Thang and T.-S. Kim, "Human Activity Recognition via 3-D joint angle features and Hidden Markov models," in Image Processing (ICIP), 2010 17th IEEE International Conference on, 26-29 Sept. 2010.
[4] M. Zhang, W. Xu, A. Sawchuk and M. Sarrafzadeh, "Sparse representation for motion primitive-based human activity modeling and recognition using wearable sensors," in Pattern Recognition (ICPR), 2012 21st International Conference on, 11-15 Nov. 2012.
[5] S. Venkatesha and M. Turk, "Human Activity Recognition Using Local Shape Descriptors," in Pattern Recognition (ICPR), 2010 20th International Conference on, 23-26 Aug. 2010.
[6] B. Li, O. Camps and M. Sznaier, "Cross-view activity recognition using Hankelets," in Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, 16-21 June 2012.
[7] M. Abidine and B. Fergani, "Evaluating C-SVM, CRF and LDA classification for daily activity recognition," in Multimedia Computing and Systems (ICMCS), 2012 International Conference on, 10-12 May 2012.
[8] L. Zhao, X. Wang, G. Sukthankar and R. Sukthankar, "Motif Discovery and Feature Selection for CRF-based Activity Recognition," in Pattern Recognition (ICPR), 2010 20th International Conference on, 23-26 Aug. 2010.
[9] H. Wang, A. Klaser, C. Schmid and C.-L. Liu, "Action recognition by dense trajectories," in Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, 20-25 June 2011.
[10] X. Wang and Q. Ji, "Learning dynamic Bayesian network discriminatively for human activity recognition," in Pattern Recognition (ICPR), 2012 21st International Conference on, 11-15 Nov. 2012.
[11] L. Breiman., Random forests. Mach. Learning, 45(1):5–32, 2001.
[12] C. Liu, Y. Kong, X. Wu and Y. Jia, "Action recognition with discriminative mid-level features," in Pattern Recognition (ICPR), 2012 21st International Conference on, 11-15 Nov. 2012.
[13] Sundaram, Narayanan, T. Brox and K. Keutzer, "Dense point trajectories by GPU-accelerated large displacement optical flow," in Computer Vision–ECCV 2010. Springer Berlin Heidelberg, 2010. 438-451.
[14] Farnebäck and Gunnar, "Two-frame motion estimation based on polynomial expansion," in Image Analysis. Springer Berlin Heidelberg, 2003. 363-370.
[15] H. Wang, M. M. Ullah, A. Klaser, I. Laptev and C. Schmid, "Evaluation of local spatio-temporal features for action recognition," in BMVC 2009 - British Machine Vision Conference, Sep. 2009.
[16] N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on (Volume:1 ), 25-25 June 2005.
[17] O. Déniz, G. Bueno, J. Salido and F. D. l. Torre, "Face recognition using histograms of oriented gradients," in Pattern Recognition Letters, Sep. 2011.
[18] A. Dhall, A. Asthana, R. Goecke and T. Gedeon, "Emotion recognition using PHOG and LPQ features," in Automatic Face & Gesture Recognition and Workshops (FG 2011), 2011 IEEE International Conference on, 21-25 March 2011.
[19] I. Laptev, M. Marszalek, C. Schmid and B. Rozenfeld, "Learning realistic human actions from movies," in Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, 23-28 June 2008.
[20] K. Lertniphonphan, S. Aramvith and T. Chalidabhongse, "Human action recognition using direction histograms of optical flow," in Communications and Information Technologies (ISCIT), 2011 11th International Symposium on, 12-14 Oct. 2011.
[21] "http://cs.nyu.edu/~fergus/teaching/vision_2012/9_BoW.pdf," [Online].
[22] D. Nister and H. Stewenius, "Scalable Recognition with a Vocabulary Tree," in Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on (Volume:2 ), 2006.
[23] C. Schuldt, I. Laptev and B. Caputo, "Recognizing human actions: a local SVM approach," in Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on (Volume:3 ), 23-26 Aug. 2004.
[24] T. K. Ho, "Random decision forests," in Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on (Volume:1 ), 14-16 Aug 1995.
[25] R. Messing, C. Pal and H. Kautz, "Activity recognition using the velocity histories of tracked keypoints," in Computer Vision, 2009 IEEE 12th International Conference on, Sept. 29 2009-Oct. 2 2009.
[26] J. Shi and C. Tomasi, "Good features to track," in Computer Vision and Pattern Recognition, 1994. Proceedings CVPR '94., 1994 IEEE Computer Society Conference on, 21-23 Jun 1994.

連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文