淡江大學覺生紀念圖書館 (TKU Library)
進階搜尋


下載電子全文限經由淡江IP使用) 
系統識別號 U0002-0706200600124600
中文論文名稱 運動影片中人物動作的自動偵測與分析:以立定跳遠為例
英文論文名稱 Automatic Detection and Analysis of Human Motion in Sports Video: A Case Study in Standing Long Jump
校院名稱 淡江大學
系所名稱(中) 資訊工程學系碩士班
系所名稱(英) Department of Computer Science and Information Engineering
學年度 94
學期 2
出版年 95
研究生中文姓名 謝勝文
研究生英文姓名 Sheng-Wen Hsieh
學號 693191610
學位類別 碩士
語文別 中文
口試日期 2006-06-06
論文頁數 68頁
口試委員 指導教授-許輝煌
委員-陳五洲
委員-王慶生
中文關鍵字 動作分析  人的偵測與追蹤  姿勢預估  基因演算法 
英文關鍵字 Motion analysis  human detection and tracking  shadow removal  pose estimation  genetic algorithms 
學科別分類 學科別應用科學資訊工程
中文摘要 關於各種的運動分析的研究越來越多,如分析網球、籃球、高爾夫球等,都有人在研究分析資料以做為訓練之用,而我們這篇論文所要做的是分析小朋友跳遠的影片,希望可以藉由電腦的幫助,將分析影片的難度降低,更進而讓系統可以提供受測者意見,使之可以了解自己動作的問題而不需要專業的老師在側協助。
在這邊我們的論文將分為兩大部分來介紹我們所使用的方法,第一部分是將人從影片中擷取出來,而在這部分中,我們將分為五個細項來處理,第一個項目是還原背景,第二個項目是取出前景物件,第三個項目是去除雜訊點,第四個項目是修補輪廓破損,第五個項目是去除陰影。
第二部分是預測骨架,在這邊我們是透過基因演算法的方法來預測骨架,透過基因演算法的特性“適者生存,不適者淘汰"的規則來預測骨架,因此在產生數代的骨架組合後,我們將可以從這些組合中得到一組最適合輪廓的骨架。
而當預測出來的骨架都能對應到影片中受測者的輪廓時,我們就可以得到一連串的動作分解,進而可以做到分析受測者的動作是否正確,將來更可以將評分的動作也加入到系統中,使這系統可以給受測者一點回饋,使受測者知道說自己的動作還有那邊可以加強,如此一來就可以讓受測者在沒有專業的體育老師在旁邊時,依然可以做自我的練習。
英文摘要 Analyses and researches toward various sport activities are broadly put in use, and these sports involve tennis, basketball, and golf, whose data are collected and analyzed as the training data. In this thesis, we examine the video of children doing long jumps, aiming to reduce the difficulty in analyzing video sequences of children who are doing long jumps with the assistance of the computer. Furthermore, the developed system can also give
comments on the testers about the problems of their movements and gestures without a professional instructor.
The proposed method consists of two parts. The first one is to retrieve human objects from the video and it can be divided into five steps -background restoration, foreground objects retrieval, noise reduction, breakage repainting, and shadow removal.
The second part is to do stick model prediction, which utilizes the characteristics of survival of the fittest in Genetic Algorithm (GA). As a result, we can obtain a stick model that is fittest to the silhouette after several generations of evolutions.
While the predicted a stick model correspond to the silhouette of testers in the video, a succession of action decomposition is then taken place to analyze the correctness of the movements. Also, a scoring function can be integrated into the system so that the testers can receive feedbacks from the system. They can understand which parts of movements should be improved and the system makes it possible that testers can do self practice even without a professional physical education instructor.
論文目次 第 1 章 緒論............................................1
1.1 研究背景與目的......................................1
1.2 論文組織簡介........................................4
第 2 章 文獻分析........................................6
2.1 動作分析............................................6
2.2 基因演算法.........................................12
第 3 章 系統架構.......................................17
3.1 系統架構簡介.......................................17
3.2 受測者的輪廓之分割.................................18
3.2.1 背景圖之建立.....................................18
3.2.2 前景物件之取出...................................19
3.2.3 雜訊點之去除.....................................21
3.2.4 輪廓中的破損處之修補.............................23
3.2.5 陰影之去除.......................................25
3.3 骨架之建立.........................................27
3.3.1 骨架表示法及適合度方程式之介紹...................27
3.3.2 初始骨架之建立...................................31
3.3.3 進化理論.........................................36
第 4 章 系統實作.......................................39
4.1 開發平台介紹.......................................39
4.1.1 Visual Studio.NET................................39
4.1.2 C# ..............................................40
4.2 系統簡介...........................................41
4.3 實驗結果與討論.....................................45
4.3.1 實驗結果.........................................45
4.3.2 討論.............................................54
第 5 章 結論與未來展望.................................57
5.1 結論...............................................57
5.2 未來展望...........................................58
參考文獻...............................................60
英文論文...............................................63
圖目錄
圖 一、動作分析步驟圖...........................................................6
圖 二、基因演算法流程.........................................................16
圖 三、(a)原始圖片 (b)建立出的背景圖...............................19
圖 四、前景物件圖.................................................................20
圖 五、八鄰居示意圖.............................................................21
圖 六、去除小雜訊點後.........................................................22
圖 七、去除大雜訊點後.........................................................23
圖 八、經過補點之後.............................................................24
圖 九、去除陰影後的結果.....................................................27
圖 十、骨架在輪廓中的表示..................................................28
圖 十一、骨架每部分與垂直線的交角..................................29
圖 十二、染色體表示法.........................................................29
圖 十三、標點的部位.............................................................31
圖 十四、骨架之建立.............................................................32
圖 十五、以染色體表示法紀錄長度值..................................33
圖 十六、以染色體表示法紀錄所在象限位置......................33
圖 十七、象限位置示意圖.....................................................33
圖 十八、骨架超出輪廓.........................................................35
圖 十九、骨架包含在輪廓中..................................................35
圖 二十、軟體使用介面.........................................................40
圖 二十一、骨架預測程式介面之ㄧ......................................43
圖 二十二、骨架預測程式介面之二......................................43
圖 二十三、骨架預測程式介面之三......................................44
圖 二十四、骨架預測程式介面之四......................................44
圖 二十五、影片中的第一張與第二張圖片..........................45
圖 二十六、第二張圖片所做出的初始組..............................46
圖 二十七、初始組中所選出做交叉配對的第一代..............46
圖 二十八、交叉配對的第二代..............................................47
圖 二十九、所有產生出來的圖片中Fs 值最小的前五組(範例一) 48
圖 三十、所有產生出來的圖片中Fs 值最小的前五組(範例二) 49
圖 三十一、另段影片中的第一張與第二張圖片..................50
圖 三十二、另段影片中所產生圖片中Fs 值最小的前五組(範例一) 51
圖 三十三、另段影片中所產生圖片中Fs 值最小的前五組(範例二) 51
圖 三十四、人工標點與系統標點之比較..............................53
圖 三十五、一連串動作預測..................................................55
圖 三十六、不太正確的預測結果..........................................56
圖 三十七、不符合輪廓的預測結果......................................56
公式目錄
公式 1 .......................................................................................26
公式 2 .......................................................................................26
公式 3 .......................................................................................30
參考文獻 [1] Hwann-Tzong Chen, Horng-Horng Lin, Tyng-Luh Liu,"Multi-object tracking using dynamical graph matching", Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume: 2 , 8-14 Dec. 2001, Pages:II-210 - II-217 vol.2
[2] Mark C.K. Yang, Jong-Sen Lee, Fellow, IEEE,Cheng-Chang Lien, and Chung-Lin Huang "Hough Transform Modified by Line Connectivity and Line Thickness", IEEE Transactions on Pattern Analysis and Machine Intelligence ,Volume 19 Issue 8 (August 1997, Pages: 905 - 910,Year of Publication: 1997 ,ISSN:0162-8828
[3] Fengliang Xu and Kikuo Fujimura, “Human Detection Using Depth and Gray Images,” Proc. IEEE Conference on Advanced Video and Signal Based Surveillance, 115 – 121, July 21-22, 2003.
[4] Chih-Yi Chiu, Shih-Pin Chao, Ming-Yang Wu, Shi-Nine Yang, and Hsin-Chih Lin "Content-Based Retrieval for Human Motion Data", to appear on Journal of Visual Communication and Image Representation. pp. 605-612, Kinmen, Taiwan, R.O.C., Aug. 17-19, 2003.
[5] A. Cavallaro, E. Salvador, and T. Ebrahimi, “Shadow-aware object-based video processing,” IEE Proc. - Vision, Image and Signal Processing, 152 (4), 398 – 406, Aug. 5, 2005.
[6] Satoshi Yonemoto, Hiroshi Nakano, and Rin-ichiro Taniguchi,“Real-time Human Figure Control Using Tracked Blobs,” Image Analysis and Processing, 2003.Proceedings. 12th International Conference on 17-19 Sept. 2003 Page(s):127 – 132
[7] Wen-Nung Lie and Ruey-Lung Chen, “Tracking moving objects in MPEG-compressed videos,” IEEE International Conference on Multimedia and Expo, 2001. ICME 2001. 22-25 Aug. 2001 Page(s):965 – 968
[8] Thakoor, N and Gao, J. “Automatic Video Object Shape Extraction and its Classification with Camera in Motion,” IEEE International Conference on Image Processing, 2005. ICIP 2005. Volume 3, 11-14 Sept. 2005 Page(s):437 - 440
[9] Haifeng Xu, Younis, A.A. , and Kabuka M.R, “Automatic moving object extraction for content-based applications,” IEEE Transactions on Circuits and Systems for Video Technology, Volume 14, Issue 6, June 2004 Page(s):796 - 812
[10] Yilmaz, A, Xin Li, and Shah, M, “Contour-based object tracking with occlusion handling in video acquired using mobile cameras,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 26, Issue 11, Nov. 2004 Page(s):1531 - 1536
[11] Dong Xu, Jianzhuang Liu, Li, X, Zhengkai Liu, and Xiaoou Tang, “Insignificant shadow detection for video segmentation,” IEEE Transactions on Circuits and Systems for Video Technology, Volume 15, Issue 8, Aug. 2005 Page(s):1058 - 1064
[12] Gevers, T, “Robust segmentation and tracking of colored objects in video,” IEEE Transactions on Circuits and Systems for Video Technology, Volume 14, Issue 6, June 2004 Page(s):776 - 781
[13] Rita Cucchiara, Costantino Grana, Massimo Piccardi, Andrea Prati, and Stefano Sirotti, “Improving Shadow Suppression in Moving Object Detection with HSV Color Information,” Proc. 2001 IEEE Intelligent Transportation Systems Conf., 334 – 339, Aug. 25-29, 2001.
[14] Kenji Shoji, Atsushi Mito, and Fubito Toyama, “Pose Estimation of a 2D Articulated Object from its Silhouette Using a GA,” Proc. 15th Int’l Conf. on Pattern Recognition, 3, 713 – 717, Sept. 3-7, 2000.
[15] Rita Cucchiara, Member, IEEE, Costantino rana,Massimo Piccardi, Member, IEEE, and Andrea Prati, Member, IEEE, “Detecting Moving Objects, Ghosts, and Shadows in Video Streams,” IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 25, NO. 10, OCTOBER 2003
[16] Liang Wang, Weiming Hu, Tieniu Tan,” Recent Development in Human Motion Analysis,” Pattern Recognition 36 (2003) 585 – 601
[17] Colin R. Reeves, Jonathan E. Rowe, “Genetic Algorithms-Principles and Perspectives”
[18] http://cindy.cis.nctu.edu.tw/AI96/team12/GA/GA.html
[19] http://www.metavista.com.tw/gademo.jsp
[20] Jenny R. Wang, Nandan Parameswaran,” Detecting Tactics Patterns for Archiving Tennis Video Clips,” IEEE Sixth International Symposium on Multimedia Software Engineering, 2004. Proceedings. 13-15 Dec. 2004 Page(s):186 - 192
[21] Wang, J.R., Parameswaran, N.,“ Analyzing Tennis Tactics from Broadcasting Tennis Video Clips, ” Proceedings of the 11th International Multimedia Modelling Conference, 2005. MMM 2005. 12-14 Jan. 2005 Page(s):102 - 106
[22] Kathleen M. Haywood (1993). Laboratory Activities for Life Span Motor Development. (2nd ed.). IL: Human Kinetics Publishers.
[23] Payne, V. Gregory, & Isaacs, Larry D. (2002). Human Motor Development (4th ed.). Toronto, London: Mayfield Publishing Company.
[24] http://www.vicon.com/
論文使用權限
  • 同意紙本無償授權給館內讀者為學術之目的重製使用,於2006-09-01公開。
  • 同意授權瀏覽/列印電子全文服務,於2006-09-01起公開。


  • 若您有任何疑問,請與我們聯絡!
    圖書館: 請來電 (02)2621-5656 轉 2281 或 來信