臺灣博碩士論文加值系統

近年來，隨著電腦視覺技術的進步及電腦運算能力的提升，移動物件追蹤系統被應用在各種不同的領域上，如：安全監視系統、醫療看護系統等應用。在眾多追蹤演算法中，許多方法容易因為需要背景模型的建立，而使得演算法僅能於固定式攝影鏡頭上做處理，有鑑於此，我們提出了一個新的追蹤演算法，並希望能在非固定式鏡頭所拍攝的影像下，追蹤畫面中任何我們感興趣的物件。
本論文所提出的移動物件追蹤演算法，針對傳統適應性粒子濾波器在適應物件大小上的問題做改善，使用了包含旋轉不變特性的區域二位元圖形的紋理資訊，以及色彩模型資訊做模型的建立，來增加追蹤準確度。並利用我們的遮蔽策略，在目標物件受到部分遮蔽時，能調整參考兩種資訊的權重進行處理；不同於以往的做法，當物件受到完全遮蔽時，改以較大的搜尋範圍及較多的樣本數目來進行目標物件之座標及尺寸的估算，使得物件能在遮蔽狀況結束後還能追蹤到該目標物件。
實驗結果顯示，我們的演算法在物件外表變形或受到外在環境改變影響下，還能進行良好的追蹤處理，並且我們能較原始的適應性粒子濾波器演算法使用較少的樣本數進行物件追蹤處理，在運算速度上亦可擁有不錯的表現。

In the last decade, object tracking systems have been widely applied in many different fields due to the rapid development of computer vision techniques and faster computing ability, such as Surveillance System, Health-Care System. In this field, many approaches require establishing background in preprocessing step. This limits tracking algorithm only be executed under a fixed camera. However, many applications are taking place in a moving camera. Accordingly, we propose a new algorithm to track rigid or non-rigid object by a moving camera.
The proposed tracking algorithm use rotation-invariant texture feature and color feature to increase the tracking correctness. The target is jointly modeled by color and texture information. We adjust the weight of each feature, so it is less sensitive to different circumstances such as partial occlusions. When fully occluded, we extend search region and double the particle number to avoid missing target if the occlusion disappear.
The experimental results reveal that our tracking method can efficiently and successfully track rigid or non-rigid object under appearance and illumination changes. Also, fewer samples are used to achieve better result than the traditional particle filter method.

摘要.........................................................I
Abstract....................................................II
誌謝.......................................................III
目錄........................................................IV
圖表目錄....................................................VI
第一章 緒論..............................................1
1.1 研究動機.................................................1
1.2 研究背景與方法...........................................3
1.3 論文組織.................................................7
第二章 移動物件追蹤系統之介紹............................8
2.1 移動物件追蹤系統架構.....................................8
2.2 色彩模式轉換............................................10
2.3 移動物件的描述..........................................12
2.3.1 核心函數..............................................13
2.3.2 目標物件之色彩分佈模型................................17
2.3.3 候選物件之色彩分佈模型................................19
2.3.4 相似度計算Bhattacharyya Coefficient...................21
第三章 移動物件追蹤演算法...............................28
3.1 全域搜尋演算法..........................................29
3.2 平均值位移演算法........................................30
3.3 粒子濾波器演算法 (Particle Filter Algorithm)............36
3.3.1 基於顏色資訊的適應性粒子濾波器演算法..................39
第四章 基於顏色與紋理資訊的適應性粒子濾波器追蹤演算法...44
4.1 演算法流程架構..........................................45
4.2 雙線性內插法............................................46
4.3 追蹤演算法..............................................49
4.3.1 候選樣本..............................................50
4.3.2 旋轉不變的區域二位元圖形..............................51
4.3.3 估算移動物體位置與大小................................54
4.3.4 目標物件之遮蔽策略....................................56
4.3.5 樣本重新取樣..........................................61
第五章 實驗結果與效能分析...............................63
5.1 實驗參數設定............................................64
5.1.1 權重函數..............................................65
5.1.2 動態傳輸方程式........................................70
5.1.3 目標物件模型之更新....................................70
5.2 實驗結果展示............................................71
5.3 執行時間分析............................................91
第六章 結論與未來研究方向...............................95
6.1 結論....................................................95
6.2 未來研究方向............................................96
參考文獻....................................................97
作者簡介...................................................100

[1] S.Y. Chien, S.Y. Ma, Liang-Gee Chen, “Efficient Moving Object Segmentation Algorithm Using Background Registration Technique,” IEEE Transaction on Circuits and System for Video Technology, Vol. 12, No. 7, pp.577-586, 2002.
[2] A.J. Lipton, H. Fujiyoshi, R.S. Patil, “Movin Target Classification and Tracking from Real-time Video,” Proc. IEEE Workshop Applications of Computer Vision, pp.8-14, 1998.
[3] F.E. Alsaqre, Y. Baozong, “Moving Object Segmentation for Video Surveillance and Conferencing Applications,” Proceedings International Conference on Communication Technology (ICCT, 2003), Vol. 2, pp.1856-1859, 2003.
[4] J. I Agbinya, D. Rees, “Multi-Object Tracking in Video, ” Real-Time Image 5, pp. 295-304, 1999.
[5] S.T. Birchfield, S. Rangarajan, “Spatiograms Versus Histograms for Region-Based Tracking,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Vol. 2, pp. 1158-1163, 2005.
[6] F. Porikli, O. Tuzel, P. Meer, “Covariance Tracking using Model Update Based on Lie Algebra,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp.728-735, 2006.
[7] R. Polana, R. Nelson, “Low Level Recognition of Human Motion,” IEEE Workshop Motion of Non-Rigid and Articulated Objects, pp. 77-82, 1994.
[8] D.S. Jang, H.I. Choi, “Active models for tracking moving objects,” Pattern Recognition, Vol. 33, pp. 1135-1146, 2000.
[9] S.K. Weng, C.M. Kuo, S.K. Tu, “Video Object Tracking using Adaptive Kalman Filter,” Journal of Visual Communication and Image Representation, Vol. 17, pp. 1190-1208, 2006.
[10] R.L. Hsu, A.M. Mohamed, A.K. Jain, “Face Detection in Color Images,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 24, No.5, pp. 696-706, 2002.
[11] J. Han, M. Feng, P.H.N. de With, “A Real-Time Video Surveillance System with Human Occlusion Handling using Nonlinear Regression,” IEEE International Conference on Multimedia and Expo, pp. 335-340, 2008.
[12] M. Mason, Z. Duric, “Using Histograms to Detect and Track Objects in Color Video,” Proceedings of Applied Imagery Pattern Recognition, pp. 154–162, 2001.
[13] J.S. Hu, C.W. Juan, J.J. Wang, “A Spatial-Color Mean-Shift Object Tracking Algorithm with Scale and Orientation Estimation,” Pattern Recognition Letters, Vol. 29, pp. 2165-2173, 2008.
[14] D. Comaniciu, V. Ramesh, P. Meer, “Real-Time Tracking of Non-Rigid Objects using Mean Shift,” IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 241-219, 2000.
[15] T. L. Hwang, J. J. Clark, “On Local Detection of Moving Edge,” Proceedings of IEEE International Conference on Pattern Recognition, Vol. 1, pp. 180-184, 1990.
[16] H. Liu, Z. Yu, H. Zha, Y. Zou, L. Zhang, “Robust Human Tracking Based on Multi-Cue Integration and Mean-Shift,” Pattern Recognition Letters, Vol. 30, pp. 827–837, 2008.
[17] C. Chang, R. Ansari, “Kernel Particle Filter for Visual Tracking,” IEEE Signal Processing Letters, Vol. 12, No. 3, 2005.
[18] K. Nummiaro, E. Koller-Meier, L. V. Gool, “An Adaptive Color-Based Particle Filter,” Image and Vision Computing, Vol. 21, pp. 99-110, 2003.
[19] R.Q. Chen, Z.H. Zhang, H.Q. Lu, H.Q. Cui, Y.K. Yan, “Particle Filter Based Object Tracking with Color and Texture Information Fusion,” Proceedings of SPIE, Vol. 7495, pp. 74952F, 2009.
[20] M.Z. Islam, C.M. Oh, C.W. Lee, “Real Time Moving Object Tracking by Particle Filter,” Proceedings of the International Symposium on Computer Science and its Applications, pp. 347-352, 2008.
[21] K. Hotta, “Adaptive Weighting of Local Classifiers by Particle Filters for Robust Tracking,” Pattern Recognition, Vol. 42, pp. 619-628, 2009.
[22] J. Wang, Y. Yagi, “Adaptive Mean-Shift Tracking with Auxiliary Particles,” IEEE Transaction on Systems, MAN, and Cybernetics, pp.1578-1589, 2009.
[23] C. Shan, T. Tan,Y. Wei, “Real-time Hand Tracking using a Mean Shift Embedded Particle Filter,” Pattern Recognition, Vol. 40, pp.1958-1970, 2007.
[24] D. Comaniciu, V. Ramesh, “Mean Shift and Optimal Prediction for Efficient Object Tracking,” IEEE International Conference on Image Processing, pp. 70-73, 2000.
[25] A. Yao, G. Wang, X. Lin, X. Chai, “An Incremental Bhattacharyya Dissimilarity Measure for Particle Filtering,” Pattern Recognition, Vol. 43, pp. 1244-1256, 2010.
[26] T. Ojala, M. Pietikainen, T. Maenpaa, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 24, No. 7, pp. 971-987, 2002.
[27] T. Ojala, M. Pietikainen, Z. XU, “Rotation-Invariant Texture Classification using Feature Distributions,“ Pattern Recognition 33, Vol. 33, pp. 43-52, 2000.
[28] T. Maenpaa, “The Local Binary Pattern Approach to Texture Analysis – Extensions and Applications,” Ph.D. Dissertation, University of Oulu, 2003.
[29] W. Zhang, S. Shan, W. Gao, X. Chen, H. Zhang, “ Local Gabor Binary Pattern Histogram Sequence (LGBPHS): A Novel Non-Statistical Model for Face Representation and Recognition,” Tenth IEEE International Conference on Computer Vision (ICCV'05), Vol. 1, pp. 786-791, 2005.
[30] I.S. Hsieh, K.C. Fan, “An Adaptive Clustering Algorithm for Color Quantization,” Pattern Recognition 21, Vol. 21, pp. 337-346, 2000.
[31] M.J. Swain, B.H. Ballard, “Color Indexing” , Int'l J. Computer Vision, Vol. 7, No. 1, pp. 11-32, 1991.
[32] D.W. Scott, Multivariate Density Estimation, New York: Wiley, pp. 24-26, 1992.