成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	林俊安 Lin, Jiun-An
論文名稱：	基於霍夫域之動態追蹤定位與辨識系統 A Dynamic Tracking and Recognition System in Hough Domain
指導教授：	楊家輝 Yang, Jar-Ferr
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電腦與通信工程研究所 Institute of Computer & Communication Engineering
論文出版年：	2009
畢業學年度：	97
語文別：	中文
論文頁數：	70
中文關鍵詞：	平均位移法、霍夫轉換
外文關鍵詞：	Mean-shift, Hough transform
相關次數：	點閱：73 下載：2
分享至:	分享至facebook 分享至twitter

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

本論文於霍夫域提出ㄧ套能夠將影像追蹤和圖像辨識做有效連結在一起，藉此達到動態視覺追蹤定位應用需求。相較於過去傳統追蹤演算法，本追蹤定位系統較不易受光線影響，同時可藉由簡單的顏色特徵，在複雜背景之下完成追蹤。我們將此套演算法應用在球拍上，在圖像和物體特徵模型巧妙設計下，實驗證實本系統亦可在球拍縮放轉動的過程中，得到不錯的追蹤定位效果。未來希望能透過偵測使用者手上拿的球拍，以及運動的軌跡來判斷使用者的姿勢跟行為。

This thesis based on Hough domain presents an effective combination of image tracking and pattern recognition to achieve needs of dynamic location-based visual tracking. Compared to traditional tracking algorithms, the proposed positioning system can track the object to be less affected by light. By further considering the color feature, the proposed system can successfully track the desired object even in complex background. With clever design features of the model, the proposed system is applied to track the racket. Simulation results show that the designed tracking system can easily identify trajectory of racket, even if it has zoom and rotation actions. In the future, we hope to totally detect the racket, which is held by the users, and the trajectory of the movement to determine the user action in the ball game.

摘要 (中文) ..............................................I
ABSTRACT (English) .......................................II
誌 謝 ....................................................III
目 錄 ....................................................IV
圖目錄 ...................................................VII
第一章 簡介 ..............................................1
1-1 目的與動機............................................1
1-2 平均位移法(Mean-Shift)簡介............................2
1-3 主動式輪廓模型(Active Contour Model)簡介..............2
第二章 影像追蹤演算法.....................................6
2-1 建構追蹤模型..........................................8
2-1-1 核函數 (Kernel Function)............................9
2-1-2 物體模型 (Object Model).............................12
2-1-3 候選目標 (Candidate Target).........................13
2-2 樣板相似度比對........................................14
2-2-1 Bhattacharyya 係數..................................15
2-2-2 預測目標物之中心位置................................17
2-3 改良式平均位移法......................................20
2-4 CgCbCr 特徵空間.......................................27
第三章 結合平均位移之霍夫域追蹤演算法.....................29
3-1 霍夫演算法之線段偵測簡介..............................29
3-2 基于霍夫域之圖像辨識機制..............................35
3-2-1 邊緣檢測 (Canny Edge Detector) .....................35
3-2-2 球拍圖像辨識 (Pattern Recognition)..................42
3-3 結合平均位移之動態圖像辨識演算法......................57
第四章實驗結果及討論......................................60
4-1 球拍在一般運動時追蹤結果..............................61
4-2 球拍前後移動時追蹤結果................................62
4-3 球拍在複雜背景時的追蹤結果............................63
第五章 結論及未來發展方向.................................66
5-1 結論 .................................................66
5-2 未來發展方向..........................................67
參考文獻 .................................................68
                                    

[1] A. Elgammal, D. Harwood, and L. Davis, “Non-Parametric Model for Background Subtraction,” Proc. IEEE Frame Rate Workshop, 1999.
[2] Fukunaga, Keinosuke, Larry D. Hostetler, “The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition,” IEEE Transactions on Information Theory, pp.32–40, 1975.
[3] Cheng, "Mean Shift, Mode Seeking, and Clustering," presented at IEEE Trans. Pattern Anal. Mach. Intell., pp.790-799, 1995.
[4] Cheng Y, “Mean shift, mode seeking, and clustering,” IEEE Trans. on pattern analysis and machine intelligence, pp. 790-799, 1995.
[5] Comaniciu D, “Ramesh V, and Meer P. Kernel-based object tracking,”IEEE Trans. on pattern analysis and machine intelligence, pp. 564-577, 2003.
[6] Comaniciu D, Meer P. “Mean shift analysis and applications, ” Proc. of the IEEE Int’l Conf. on Computer Vision, pp. 1197-1203, 1999.
[7] Kass, M., A. Witikin and D. Terzopoulos, “Snakes: Active contour models,” International Journal of Computer Vision, vol.1, no.4, pp. 321-331, 1978.
[8] Paragios, Nikos and R. Deriche, “Geodesic active contours and level sets for the detection and tracking of moving objects,” IEEE Transactions on Pattern Analysis and Machine intelligence, vol.22, pp. 266-280, 2000.
[9] T.-L. Liu and H.-T. Chen, “Real-time tracking using trust-region methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 3, pp. 397-402, 2004.
[10] M. Bray, E. Koller-Meier, and L. Van Gool, “Smart particle filtering for 3D hand tracking,” Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, pp. 675-680, 2004.
[11] Duda, R. O. and P. E. Hart, “Use of the Hough Transformation to Detect Lines and Curves in Pictures,” Comm. ACM, Vol. 15, pp. 11-15, 1972.
[12] J. F. Canny, “A computational approach to edge detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, pp. 679-698, 1986.

校內：2014-08-26公開
校外：2014-08-26公開

簡易檢索 / 詳目顯示

相關論文