臺灣博碩士論文加值系統

移動物體的追蹤在電腦視覺的應用已經是個愈趨重要的研究主題。多數的論文採用線性區塊映對法或卡門濾波器等以預測為主的方法來對物體做追蹤。在我們的論文中提出一個以物體特徵為依據的有效追蹤方法。我們的方法探討兩個重要的移動物件：車輛及行人。為了得到較正確的物件特徵值，物體的外形首先必須被準確的攫取出來，有三個步驟被提出來偵測物體的外形。五個可供判別物件的分類特徵也被設計出來，我們將在內容中詳細描述出這五種特徵的分析結果。我們設計一個倒傳遞類神經網路來將特徵做分類，並根據分類結果設計一個追蹤法則。我們會用一連串的影像序列來驗證我們的實驗結果。在我們的實驗中總共使用了1343個物體來做有效的物件分類，其中包括車輛有469個，行人有874個。而在物件的追蹤上，我們用實際環境的影像序列來做追蹤以呈現實驗的結果。

Moving object tracking has been an important research topic in numerous computer vision applications. Most papers adopt a prediction-based approach that uses linear block matching and Kalman filter. In this paper, an effective tracking approach using object’s features is proposed. Two important kinds of moving objects: pedestrian and vehicles, are studied in our approach. Exact object’s shape is extracted first in order to obtain accurate features of the object. Three preprocessing steps are proposed to detect the exact object’s shape. Five discriminate features are then extracted for each object. Detail analysis of the five features for the classification of object is described. A tracking scheme by classifying the features with a back-propagation neural network is invented. The proposed approach is verified through several image sequences. 1343 objects, including 469 vehicles and 874 pedestrians, can be effectively tracked in our experiments.

摘要 I
ABSTRACT II
誌謝 III
目錄 IV
表格目錄 VI
圖目錄 VII
第一章 緒論 1
1.1 研究動機 1
1.2 相關研究 2
1.3 系統架構 4
1.4 論文架構 8
第二章　　物體偵測 9
2.1 差異偵測 9
2.2 區塊增強 17
2.3 物體攫取 21
第三章　　物體表示法 26
3.1 分散度(Dispersedness) 27
3.2 變異係數(Coefficient of Variation，CV) 29
3.2.1. 中心點到輪廓的距離變異係數(CVdistance) 29
3.2.2. 紋理變異係數(CVtexture) 30
3.3 幾何比例 31
3.4 特徵分析 32
3.4.1. 相關性分析 33
3.4.2. 判別分析 34
第四章　　分類及追蹤 41
4.1 分類 41
4.2 追蹤 44
第五章　　實驗結果與討論 47
第六章　　結論及未來工作 55
參考文獻 57

[1] E. Stringa and C. S. Regazzoni, “Real-Time Video-Shot Detection for Scene Surveillance Applications,” IEEE Transactions on Image Processing, vol. 9, no. 1, pp. 69-80, Jan 2000.
[2] E. Rowe, “The Los Angeles Automated Traffic Surveillance and Control System,” IEEE Transactions on Vehicular Technology, vol. 40, no. 1, pp. 16-20, February 1991.
[3] H. Nakano, “Classifying the Motions of Human Body by Using Gabor Wavelets,” International Conference on Pattern Recognition, pp. 3691-3694, 2000.
[4] H. Fujiyoshi and A. Lipton, “Real-time human motion analysis by image skeletonization,” Fourth IEEE Workshop on Application of Computer Vision, pp. 19-21, October 1998.
[5] G. L. Foresti, “A Real-Time System for Video Surveillance of Unattended Outdoor Environments,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 8, no. 6, pp. 697-704, October 1998.
[6] M. Rossi and A. Bozzoli, “Tracking and Counting Moving People,” International Conference on Pattern Recognition, pp. 212-216, 1994.
[7] J. W. Kim, K. S. Choi, B. D. Choi, and S. J. Ko, “Real-time Vision-based People Counting System for the Security Door,” International Technical Conference on Circuits/Systems Computers and Communications, pp. 1416-1419, 2002.
[8] Z. Zhu1, G. Xu, B. Yang, D. Shi, and X. Lin, “VISATRAM: a real-time vision system for automatic traffic monitoring,” Image and Vision Computing, vol. 18, no. 10, pp. 781-794, July 2000.
[9] J. K. Aggarwal and Q. Cai, “Human motion analysis: a review,” Computer Vision and Image Understanding, vol. 73, no. 3, pp. 428-440, 1999.
[10] Lipton, H. Fujiyoshi, and R. Patil, “Moving target classification and tracking from real-time video,” IEEE Workshop on Application of Computer Vision, pp. 8 — 14, October 1998.
[11] D. Hsu, J. Leu, S. Chen, W. Chang, and W. Fang, “Using Shape Feature Matching to Track Moving Objects in Image Sequences,” IEEE International Conference on Multimedia and Expo, pp. 785-788, 2000.
[12] S. Osowski and D. D. Nghia, “Fourier and wavelet descriptors for shape recognition using neural networks - a comparative study,” Pattern Recognition, vol.35, pp. 1949-1957, 2002.
[13] C. P. Diehl and J. B. Hampshire II, “Real-time Object Classification and Novelty Detection for Collaborative Video Surveillance,” Proceedings of the 2002 International Joint Conference on Neural Networks, vol. 3, pp. 2620 -2625, 2002.
[14] D. S. Jang and H. I. Choi, “Active models for tracking moving objects,” Pattern Recognition, vol. 33, pp. 1135-1146, 2000.
[15] D. S. Jang, S. W. Jang, and H. I. Choi, “2D Human Body Tracking with Structural Kalman Filter,” Pattern Recognition, vol. 35, no. 10, pp. 2041-2049, October 2001.
[16] D. S. Jang, G. Y. Kim, and H. I. Choi, “Model-based tracking of moving object,” Pattern Recognition, vol. 30, no. 6, pp. 999-1008, June 1997.
[17] G. L. Foresti and C. S. Regazzoni, “New trends in video communications, processing and understanding in surveillance applications,” IEEE International Conference on Image Processing, 2001 Tutorial.
[18] R. C. Gonzalez and R. E. Woods, Digital image processing, 2nd Edition, Prentice Hall, 2003.
[19] V. Khanna, P. Gupta, and C. J. Hwang, “Finding connected components in digital images by aggressive reuse of labels,” Image and Vision Computing Journal, vol.20, no. 8, pp. 557-568, June 2002.
[20] B. Heisele, U. Kressel, and W. Ritter, “Tracking Non-rigid, Moving Objects based on Color Cluster Flow,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 253-257, 1997.
[21] E. Saykol, U. Güdükbay, and Ö. Ulusoy, “A Histogram-Based Approach for Object-Based Query-by-Shape and Color in Multi-Media Databases,” Technical Report BU-CE-0201, Bilkent University, Ankara, Turkey, 2002.
[22] F. Ziliani and A. Cavallaro, “Image Analysis for Video Surveillance Based on Spatial Regularization of a Statistical Model-Based Change Detection,” International Conference on Image Analysis and Processing, pp. 1108-1111, September 1999.
[23] R. Cutler and L. Davis, “View-based Detection and Analysis of Periodic Motion,” International Conference on Pattern Recognition, Brisbane, Australia, August 1998.
[24] S. Pascahlakes and P. Lee, “Pattern Recognition in Grey Level Images using Moment Based Invariant Features,” IEE 7th International Conference on Image Processing and its Applications, pp. 245-249, 1999.