臺灣博碩士論文加值系統

近年來在影像處理中，車輛檢索、交通監控系統以及智慧型導航系統一直為熱烈探討的話題。車輛方向偵測是一項不可或缺的關鍵技術，因為在這些系統中，我們常常要進行車輛比對，然而在不同角度上欲辨識兩輛車是否相同為非常困難的，且不易達到理想的比對結果。因此本篇論文將提出一個高穩定性及高準確度的方法去偵測靜態影像中車輛的方向定位。 本系統將車子細分為八個方向，首先我們利用一個金屬色的模組偵測在影像中可能為金屬的區域，此模組不管在複雜背景或是不同光線下都有相當穩定的結果。接著將金屬色分布、主軸方向以及邊緣特徵建立成一個特徵描述器。最後我們使用Ncut分類器作車子方向的分類。由實驗結果得知，我們所提出來的方法即使在黑夜、雨天或是室內停車場都有相當優異的表現。

This paper proposes a novel approach for vehicle orientation detection using “vehicle color” and edge information based on clustering framework. To extract the “vehicle color”, this thesis proposes a novel color transform model which is global and does not need to be re-estimated for any new vehicles or new images. This model is invariant to various situations like contrast changes, background and lighting. Compared with traditional methods which use motion feature to determine vehicle orientations, this thesis uses only one still image to achieve this task. After feature extraction, the normalized cut spectral clustering (N-cut) is used for vehicle orientation clustering. The N-cut criterion tries to minimize the ratio of the total dissimilarity between groups to the total similarity within the groups. Then, the vehicle orientation can be detected using the eigenvectors derived from the N-cut result. Experimental results reveal the superior performances in vehicle orientation estimation.

摘 要 i
Abstract ii
List of Figures v
List of Tables vii
Chapter 1 Introduction 1
Chapter 2 System Overview 4
Chapter 3 Vehicle Description 6
3.1 Vehicle Color Descriptor 6
3.1.1 Connected Components Labeling 9
3.1.2 Vehicle Color Distribution 10
3.1.3 Vehicle Color Orientation 13
3.2 Vehicle Edge Descriptor 14
3.3 Integration and Similarity Measurement 15
Chapter 4 Spectral Clustering 16
4.1 Normalized Cut Clustering 17
Chapter 5 License Plate Extraction 19
Chapter 6 Experimental Results 24
6.1 Condition 1: Background 25
6.2 Condition 2: Weather 27
6.3 Condition 3: Lighting 31
6.4 Condition 4: Contrast 34
6.5 Condition 5: Occlusion 37
6.6 Condition 6: Complex foreground 40
Chapter 7 Conclusions 43
References 44

[1]O. k. Al-Shaykh and J. F. Doherty, “Invariant image analysis based on Radon transform and SVD,” IEEE Transactions on Circuits and Systems, pp.123-133, Feb. 1996.
[2]J. W. Hsieh, S. H. Yu, and Y. S. Chen, “Morphology-based license plate detection from complex scene,” Journal of Electronic Imaging, vol. 11, no. 4, pp. 507-516,2002.
[3]D. Huawu and D. A. Clausi, “Gaussian MRF rotation-invariant features for image classification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.26, pp.951 - 955, July 2004.
[4]R. Cucchiara, M. Piccardi, and P. Mello, “Image analysis and rule-based reasoning for a traffic monitoring,” IEEE Transactions on Intelligent Transportation Systems, vol.1, no.2, pp.119-130, June 2002.
[5]G. L. Foresti, V. Murino, and C. Regazzoni, “Vehicle recognition and tracking from road image sequences,” IEEE Transactions on Vehicular Technology, vol.48, no.1, pp.301-318, Jan. 1999.
[6]V. Kastinaki, V. Zervakis, and K. Kalaitzakis, “A survey of video processing techniques for traffic applications,” Image and Vision Computing, vol.21, no.4, pp.359-381, 2003.
[7]J. Wu, X. Zhang, and J. Zhou, “Vehicle detection in static road images with PCA-and- wavelet-based classifier,” Proceedings of IEEE International conference on Intelligent Transportation Systems, pp.745-749, 2001.
[8]Z. Sun, G. Bebis, and R. Miller, “On-road vehicle detection using Gabor filters and support vector machines,” IEEE International Conference on Digital Signal Processing, vol.2, pp.1019-1022, 2002.
[9]M. Bertozzi, A. Broggi, and S. Castelluccio, “A real-time oriented system for vehicle detection,” Journal of Systems Architecture, pp. 317-325, 1997.
[10]Y. Wang and H. Zhang, “Content-based image orientation detection with support vector machines,” Proceeding of IEEE Workshop on Content-Based Access of Image and Video Libraries, pp.17-23, 2001.
[11]A. Vailaya, H.J. Zhang, and A. Jain, “Automatic image orientation detection,” IEEE Transactions on Image Processing, vol. 11, no. 7, pp. 746-755, 2002.
[12]K. Mikolajczyk and C. Schmid, “Scale and affine invariant interest point detectors,” International Journal of Computer Vision, pp.63–86, 2004.
[13]L. W. Tsai, J. W. Hsieh, and K. C. Fan, “Vehicle detection using normalized color and edge map,” IEEE International Conference on Image Processing, vol.2, pp.588-601, 2005. (also to appear in IEEE Transactions on Image Processing.)
[14]S. Belongie, J. Malik, and J. Puzicha, “Shape matching and object recognition using shape contexts,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 4, pp. 509-522, Apr. 2002.
[15]J. Shi and J. Malik, “Normalized cuts and image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no.8, pp.888-905, August 2000.
[16]I. S. Dhillon, Y. Guan, and B. Kulis, “Kernel k-means, spectral clustering and normalized cuts,” Proceedings of International Conference on Knowledge Discovery and Data Mining, pp. 551–556, Aug. 2004.
[17]R. Kannan, S. Vempala, and A. Vetta . “On clusterings- good, bad and spectral,” Proceedings 41st Annual Symposium on Foundations of Computer Science, pp.367-377, 2000.
[18]S. X, Yu and J. Shi, “Multiclass spectral clustering,” Proceedings of International Conference on Computer Vision, pp. 313-319, 2003.
[19]P. Chan, M. Schlag, and J. Zien, “Spectral k-way ratio cut partitioning and Clustering,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 13, pp. 1088–1096, 1994.
[20]S. Y. Kim, S. Y. Oh, J. K. Kang, Y. W. Ryu, K. Kim, S. C. Park, and K. H. Park, “Front and rear vehicle detection and tracking in the day and night times using vision and sonar sensor fusion,” Proceeding of Intelligent Robots and System, Canada, pp. 2173-2178, Aug. 2005.
[21]R. Schweiger, H. Neumann, and W. Ritter,“Multiple-cue data fusion with particle filters for vehicle detection in night view automotive applications,” Proceeding of IEEE Intelligent Transportation Systems, pp.753-758, June. 2005.
[22]L. D. Stefano and A. Bulgarelli, “A simple and efficient connected components labeling algorithm,” Proceedings of the 10th International Conference on Image Analysis and Processing, pp.322-327, 1999.
[23]D. Guo et al., “Color modeling by spherical influence field in sensing driving environment,” Proceeding of IEEE Intelligent Vehicles Symposium, pp. 249- 254, Oct. 3-5 2000.
[24]J. C. Rojas and J. D. Crisman, “Vehicle detection in color images,” IEEE Conference on Intelligent Transportation System, pp.403-408, Nov. 9-11, 1997.
[25]N. Zeng and J. D. Crisman, “Vehicle matching using color”, IEEE Conference on Intelligent Transportation System, pp.206-211, Nov. 9-11, 1997.
[26]P. Soundararajan and S. Sarkar, “Investigation of measures for grouping by graph partitioning”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol.1, pp. 239-246, 2001.
[27]Z.Wu and R. Leahy. An optimal graph theoretic approach to data clustering: Theory and its application to image segmentation, pp. 1101-1113, Nov 1993.
[28]S. Sarkar and P.Supervised,” Supervised learning of large perceptual organization: graph spectral partitioning and learning automata,” IEEE Transactions Pattern Analysis and Machine Intelligence, pp. 504-525, May 2000.