簡易檢索 / 詳目顯示
| 研究生： |
劉明哲 Liu, Ming-Je |
|---|---|
| 論文名稱： |
彩色游泳影片中之泳姿分類 |
| 指導教授： |
廖文宏
Liao, Wen-Hung |
| 學位類別： |
碩士
Master |
| 系所名稱： |
理學院 - 資訊科學系 |
| 論文出版年： | 2004 |
| 畢業學年度： | 92 |
| 語文別： | 英文 |
| 論文頁數： | 64 |
| 中文關鍵詞： | 游泳 、泳姿 、運動影片 |
| 外文關鍵詞： | swim, swimming style, sports video |
| 相關次數： | 點閱：226 下載：32 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
本論文的主要目的是建立一套泳姿自動分類系統，利用電腦視覺中影像處理技術，輔以資料分析技術，即時且自動的分析在一段從岸邊水上拍攝，包含單一泳者向著鏡頭方向游泳的彩色影片中，泳者所進行的姿勢。首先我們利用膚色模型分離出影像中屬於游泳者手臂的區域。接下來，我們分析這些區域的特徵，例如長寬比以及斜率、面積等。最後，基於連續影像中每個單一畫面的手臂區域特徵，利用一個評分系統來判斷該泳者目前所進行的是哪一種游泳姿勢，分為蝶式、仰式、蛙式、自由式等四種泳姿。在實驗結果中，我們所提出的方法對於從http://swim.ee網站上下載的50段影片中，四種泳姿的分類達到了百分之百的正確性。
In this thesis, we present a robust method to classify swimming styles from live color video sequences based on the features extracted from the upper-body of the swimmer. In our approach, potential body parts are first extracted using a simple skin color model. Next, the dominant components in the segmented regions are selected according to quantitative measures such as the aspect ratio and the area. Regression analysis is then performed to calculate the relative position of the constituent body parts. Finally, a scoring system is constructed to carry out the classification of four strokes, including butterfly, backstroke, breast stroke, and freestyle. Experimental results demonstrate the validity and efficiency of our proposed approach.
CHAPTER 1 Introduction.......................................1
1.1 Motivation............................................1
1.2 Overview..............................................2
CHAPTER 2 Related Work.......................................7
CHAPTER 3 System Framework..................................11
3.1 Color-based Segmentation............................11
3.2 Connected Component Detection.......................15
3.3 Regression Analysis.................................18
3.4 Motion Classification...............................22
3.4.1 Arm movements in butterfly stroke.............22
3.4.2 Arm movements in backstroke ..................25
3.4.3 Arm movements in breaststroke ................27
3.4.4 Arm movements in freestyle (front crawl) .....29
3.4.5 Motion classification system .................31
CHAPTER 4 EXPERIMENTAL RESULTS AND DISCUSSIONS .............43
4.1 Experimental Environment............................43
4.2 Experimental Setup..................................47
4.3 Experimental Result.......s.........................48
4.4 Discussions.........................................56
CHAPTER 5 CONCLUSIONS.......................................58
References..................................................62
【1】 J. K. Aggarwal, Q. Cai, W. Liao and B. Sabata. 1998. Nonrigid motion analysis - articulated and elastic motion. Computer Vision and Image Understanding 70:2 142-156.
【2】 H. Zhang, Y. Gong, S. Smoliar and S. Tan. 1994. Automatic Parsing of News Video. Proc. of IEEE Conference on Multimedia Computing and Systems 45-54.
【3】 MPEG-7: Context and Objectives (V.7). 1998. ISO/IEC JTC1/SC29/WG11 N2207, MPEG98.
【4】 ATVEF http://www.atvef.com
【5】 A. Ekin, A. Tekalp, and R. Mehrotra. 2003. Automatic Soccer Video Analysis and Summarization. in Symp. Electronic Imaging: Science and Technology: Storage and Retrieval for Image and Video Databases.
【6】 Yong Rui, Anoop Gupta, Alex Acero. 2000. Automatically Extracting Highlights for TV Baseball Programs. Proc. of the ACM Multimedia 105-115.
【7】 V. Kobla, D. DeMenthon, and D. Doermann. 2000. Identification of sports videos using replay, text, and camera motion features. Proc. of the SPIE Conference on Storage and Retrieval for Media Databases 3972 332-343.
【8】 G. Iyengar and A. Lippman. 1998. Models for automatic classification of video sequences. Storage and Retrieval for Image and Video Databases 3312 216-227.
【9】 McGee, T. and N. Dimitrova. 1999. Parsing TV Program Structures for Identification and Removal of Non-Story Segments. in SPIE Conf. on Storage and Retrieval for Image and Video Databases.
【10】 Y. Ariki and Y. Sugiyama. 1999. Classification of TV sports news by dct features using multiple subspace method. Proc. of the SPIE Conference on Storage and Retrieval for Image and Video Databases 3656 243-251.
【11】 How-Lung Eng, Kar-Ann Toh, Alvin H. Kam, Junxian Wang, Wei-Yun Yau. 2003. An Automatic Drowning Detection Surveillance System for Challenging Outdoor Pool Environments. International Conference on Computer Vision 532-539.
【12】 Rui, Y., Gupta, A. & Acero, A. 2000. Automatically extracting highlights for TV baseball programs. Proceedings of ACM Multimedia 105-115.
【13】 P. Chang, M.Han, and Y.Gong. 2002. Extract highlights from baseball game video with hidden markov models. In Proceedings of International Conference on Image Processing 609-612.
【14】 M. Jones and J. Rehg. 1999. Statistical Color Models with Application to Skin Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 274-280.
【15】 J. Yang, W. Lu, and A. Waibel. 1998. Skin-color Modeling and Adaptation. Proceedings of ACC 687-694.
【16】 Vezhnevets V., Sazonov V., Andreeva A. 2003. A Survey on Pixel-Based Skin Color Detection Techniques. Proc. Graphic 85-92.
【17】 R. C. Gonzalez and R. E. Woods. 2002. Digital Image Processing, Addison-Wesley Publishing.