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：	林建仲 Lin, Jiann-Jong
論文名稱：	基於多解析觀念與條件線性濾波器之有效影像序列為基礎的點追蹤演算法 Efficient Image Sequence-Based Point Tracking with Multiresolution Concept and Conditional Linear Filter
指導教授：	郭淑美 Guo, Shu-Mei
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 資訊工程學系 Department of Computer Science and Information Engineering
論文出版年：	2006
畢業學年度：	94
語文別：	英文
論文頁數：	60
中文關鍵詞：	條件線性濾波器、多項式插補、點追蹤、高斯金字塔、多解析
外文關鍵詞：	Conditional linear filter, multiresolution, polynomial interpolation, point tracking, gaussian pyramid.
相關次數：	點閱：94 下載：1
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

　　　　　　　　　　摘要
在本論文中，我們結合多解析觀念與條件線性濾波器(conditional linear filter) 產生一個有效影像序列為基礎的點追蹤演算法。在傳統影像序列為基礎的點追蹤方法中，存在兩個問題尚待解決，第一個問題是當追蹤的目標位移量太大的時候，追蹤器可能無法負荷而造成追蹤失敗。另一個問題是如果出現遮蔽物或影像受到汙染可能產生不正確的追蹤結果。為了改善這兩個缺點，我們利用高斯金字塔為基礎的多解析觀念和條件線性濾波器，使得我們的追蹤器能夠適用於較大的位移量，如此特性亦使得我們也能夠間隔幾張影像去追蹤目標點。另外，我們提出以多項式插補的方式去重建完整的追蹤軌跡，如此當遮蔽現象發生時，追蹤器還是能準確的預測目標位置，也有效的改善追蹤所需花費的時間，實驗數據顯示這建議的方法得到一個良好的追蹤效率與結果。

　　　　　　　　　　Abstract
An　efficient image sequence-based point tracker with multiresolution concept and conditional linear filter (CLF) is proposed in this paper. Two common problems in literature on image sequence-based point tracking are discussed in this paper. The first problem is that the tracker may fail when the tracking point moves too large. As for the second one, the tracked target may vanish when the occlusion occurs. To improve these drawbacks, the Gaussian pyramid-based multiresolution concept and the conditional linear filter are utilized in this paper, so that the proposed tracker is robust to a larger motion. Thus, it is able to track the target point when a number of frames are skipped. Besides, the polynomial interpolation is proposed to get a whole tracking trajectory, so that it works well for the tracking when the occlusion occurs and significantly improves the execution time. Experimental results reveal the proposed approach yields a satisfied tracking performance and efficiency.

Table  of  Contents
Abstract..................................	ii
Table  of  Contents.........................	iv
List  of  Tables............................	vi
List  of  Figures...........................	vii
Chapter　 1 　Introduction....................	1
Chapter 　2 　Background......................	4
2.1　	Conditional Linear Filter..............	4
2.1.1　	Conditional linear minimum variance estimator..................	6
2.1.2　	Tracking with conditional linear filter........................	7
2.1.3　	Application to point tracking..................................	9
2.1.3.1　	conditional dynamic equation...................................	9
2.1.3.2　	conditional measurement equation...............................	12
2.1.3.3　	estimation of measurement noise covariance.....................	15
2.1.3.4　	conditional linear filter algorithm............................	18
2.2　	Gaussian pyramid...............................................	20
2.2.1　	Gaussian pyramid generation....................................	20
2.2.2　	Generating kernel..............................................	21
2.2.3　	Example of the Gaussian pyramid................................	22
Chapter　 3　 Proposed Tracker...........................................	26
3.1　	Motion estimation phase........................................	27
3.2　	Estimation of the affine model.................................	30
3.3　	Proposed Algorithm	............................................. 33
3.4　	Polynomial Interpolation.......................................	35
3.4.1　	Application to construct point trajectory......................	35
Chapter　 4 　Experimental Results.......................................	38
4.1　	Speed of execution.............................................	39
4.2　	Tracking with skipped frames...................................	40
4.3　	Estimated trajectories.........................................	42
4.4　	The performance of the interpolation...........................	53
Chapter　 5 　Conclusions................................................	57
References..............................................................	58


                                    

[1] 　Y. Mezouar and F. Chaumette, “Model-free optimal trajectories in the image space: application to robot vision control,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, vol. 1, pp.I-1155-I-1162, Dec.2001.
[2] 　P. Sturm, “Structure and motion for dynamic scenes-the case of points moving in planes,” in Proc. IEEE Eur. Conf. Computer Vision, vol. 2, pp. 867-882, 2002.
[3] 　J. Shi and C.Tomasi, “Good features to track,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 593-600, Jun.1994.
[4] 　T. Tommasini, A. Fusiello, E. Trucco, and V. Roberto, “Making good features track better,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 178–183, Jun. 1998.
[5] 　H. Jin, P. Favaro, and S. Soatto, “Real-time feature tracking and outlier rejection with changes in illumination,” in Proc. IEEE 8th Int. Conf. Computer Vision, vol. 1, Jul. 2001, pp. 684–689.
[6] 　E. Arnaud, E. Memin, and B. Cernushi Frias, “A robust stochastic filter for point tracking in image sequences,” In Asian Conference on Computer Vision, ACCV'04, Jan. 2004.
[7] 　E. Arnaud and E. Memin. “Optimal importance sampling for tracking in image sequences: application to point tracking,” In European Conference on Computer Vision, ECCV'04, Prague, Republique Tcheque, Mai. 2004.
[8] 　E. Arnaud, E. Memin, and B. Cernuschi-Frias, “Conditional Filters for Image Sequence-Based Tracking—Application to Point Tracking,” IEEE Trans. on image processing, vol. 14, no. 1, pp. 63–79, Jan. 2005.
[9] 　R. Kalman, “A new approach to linear filtering and prediction problems,” Trans. ASME J. Basic Eng., pp. 35–45, 1960.
[10] 　M. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, “A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking,” IEEE Trans. Signal Process., vol. 50, no. 2, pp. 174–188, Feb. 2002.
[11] 　A. Doucet, S. Godsill, and C. Andrieu, “On sequential Monte Carlo sampling methods for Bayesian filtering,” Stat. Comput., vol. 10, no. 3, pp.197–208, 2000.
[12] Y. Bar-Shalom and T. Fortmann, “Tracking and data association,” New York: Academic, 1988.
[13] J. Odobez and P. Bouthemy, “Robust multiresolution estimation of parametric motion models,” J. Vis. Commun. Image Rep., vol. 6, no. 4, pp.348–365, 1995.
[14] F. Meyer and P. Bouthemy, “Estimation of time-to-collision maps from first order motion models and normal flows,” In Proc. 11th Intern. Conf. on Pattern Recognition, The Hague, pp 78-82, 1992.
[15] M. J. Black, “The robust estimation of multiple motions: parametric and piecewise-smooth flow fields,” Computer Vision and Image Understanding, Vol.63, No.1, pp.75-104, Jan.1996.
[16] A. Singh and P. Allen, “Image-flow computation: an estimation-theoric framework and a unified perspective,” Comput. Vis., Graph., Image Process.: Image Understanding, vol. 56, no. 2, pp. 152–177, 1992.
[17] K. Nickels and S. Hutchinson, “Estimating uncertainty in SSD-based feature tracker,” Image Vis. Comput., vol. 20, no. 1, pp. 47–58, 2002.
[18] P. J. Burt and E. H. Adelson, “The laplacian pyramid as a compact image code,” IEEE Trans on communications, vol. com-31, no.4, April 1983.
[19] P. J. Burt, “Fast filter transforms for image processing,” Computer Graphics, Image Processing, vol . 6, pp. 20-51, 1981.
[20] I. E. G. Richardson, “Video codec design,” John Wiley & Sons, 2002.
[21] I. E. G. Richardson, “H.264 and mpeg-4 video compression,” John Wiley & Sons, 2003.
[22] Y. Wang, J. Ostermann, and Y. Zhang, “Video processing and communications,” Prentice-Hall, 2002.
[23] W. J. Gillespie and D.T. Nguyen, “Robust estimation of camera motion in mpeg domain,” Proceedings of IEEE Tencon 2004, vol .1, pp. 395-398, Nov. 2004.
[24] 李辰邦, “適用於二維影像/三維視訊放大/ 縮小的三維離散餘弦轉換對,”成功大學資訊工程所, 2005.

校內：立即公開
校外：2006-08-09公開

簡易檢索 / 詳目顯示

相關論文