跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 蔡洛緯
Luo-Wei Tsai
論文名稱： 以正規化色彩與邊緣資訊作車輛偵測
Vehicle Detection Using Normalized Color and Edge Map
指導教授： 范國清
Kuo-Chin Fan
口試委員:
學位類別： 碩士
Master
系所名稱： 資訊電機學院 - 資訊工程學系
Department of Computer Science & Information Engineering
畢業學年度： 93
語文別： 英文
論文頁數： 58
中文關鍵詞： 邊緣資訊 、貝氏分類器 、色彩空間轉換 、車輛偵測
外文關鍵詞： color transform, vehicle detection, Bayesian classifier, edge maps
相關次數： 點閱：7  下載：0 
分享至:
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

    • 本篇論文提出一種新穎的車輛偵測方法。對於彩色影像中之車輛，利用色彩與邊緣資訊加以偵測並確認。大多數過去的方法皆採用移動資訊(Motion features)，即假設車輛為影像中之移動物，但此法對於靜止之車輛完全失效。本文提出一種新穎的色彩空間轉換方法，如同人臉偵測時會先尋找膚色區域一般，快速地找出影像中屬於車輛顏色之像素點。由於車輛具有各種不同之顏色，同時戶外環境伴隨著季節與天候不同，複雜的光線因素導致極少的論文採用色彩資訊作車輛偵測。而本文所提之色彩空間轉換方式則為一強有力之工具，足以在不同的光線條件下區分車輛與背景之像素點。
    在找出可能屬於車輛之像素點後，本文結合三種有效之特徵，分別為角點（corners）、邊緣資訊(edge maps)與小波轉換之係數，用以建構一連串且多重維度(multi-channel)之車輛分類器。此分類器對輸入影像中可能之車輛像素點作有效之確認。由於先前已利用色彩資訊濾除大量無關的背景像素點，故此確認步驟將可快速且有效的執行。實驗結果證明結合整體色彩資訊與局部邊緣資訊之車輛偵測方式是強而有效的。平均偵測率達到94.5％

    In this thesis, a novel approach for detecting vehicles using color and edge information from static images is presented. Different from traditional methods which use motion features to detect vehicles, the proposed method introduces a new color transform model to find important “vehicle color” for the quick finding of possible vehicle candidates. Since vehicles have various colors under different weather and lighting conditions, seldom works were proposed for the detection of vehicles using colors. The proposed new color transform model has extremely excellent capabilities in identifying vehicle pixels from background ones even though the pixels are under varying illuminations.
    After finding possible vehicle candidates, three important features including corners, edge maps, and coefficients of wavelet transform are used for constructing a cascade and multi-channel classifier. According to this classifier, an effective scanning is performed to verify all possible candidates. The scanning can be quickly achieved because most background pixels are eliminated by the color feature. Experimental results show that the integration of global color feature and local edge feature is powerful in the detection of vehicles. The average accuracy rate of vehicle detection is 94.5%.

    CONTENT CHAPTER 1 INTRODUCTION 1 1.1 MOTIVATION 1 1.2 REVIEW OF RELATED WORKS 2 1.3 OVERVIEW OF THE PROPOSED SYSTEM 5 CHAPTER 2 CONVENTIONAL METHODS FOR DATA ANALYSIS 7 2.1 KARHUNEN-LOE`VE TRANSFORM 8 2.2 BAYESIAN CLASSIFIER. 10 2.3 NEAREST – NEIGHBOR CLUSTERING ALGORITHM 11 CHAPTER 3 VEHICLE COLOR DETECTOR 13 3.1 COLOR FEATURES FOR DIMENSIONALITY REDUCTION 15 3.2 PIXELS CLASSIFICATION USING BAYESIAN CLASSIFIER 19 3.3 PIXELS CLASSIFICATION USING NEURAL NETWORK 20 3.4 COLOR CLASSIFICATION RESULT 25 CHAPTER 4 VEHICLE VERIFICATION 27 4.1 VEHICLE HYPOTHESIS 27 4.2 VEHICLE FEATURES 28 4.2.1 Contour feature 28 4.2.2 Wavelet Coefficients 33 4.2.3 Corner Features 36 4.3 INTEGRATION AND SIMILARITY MEASUREMENT 37 4.4 VERIFICATION PROCEDURE 39 CHAPTER 5 EXPERIMENTAL RESULTS 42 5.1 DATA SET 42 5.2 PERFORMANCE ANALYSIS OF PIXELS CLASSIFICATION 42 5.3 DETECTION RESULT IN VARIOUS ENVIRONMENTS 44 CHAPTER 6 DISCUSSIONS AND CONCLUSIONS 47 6.1 DISCUSSIONS 47 6.2 CONCLUSIONS 47 REFERENCES 49

    References
    [1] Z. Sun, G. Bebis, and R. Miller, “On-road vehicle detection using optical sensors: a view,” 2004 IEEE Intelligent Transportation Systems Conference, pp.585-590, Washington, D.C., USA, Oct. 3-6, 2004.
    [2] V. Kastinaki, M. Zervakis, and K. Kalaitozakis, “A survey of video processing techniques for traffic applications,” Image, Vision, and Computing, vol. 21, no. 4, pp.359-381, April 2003.
    [3] R. Cucchiara, P. Mello, M. Piccardi, “Image analysis and rule-based reasoning for a traffic monitoring,” IEEE Trans. on Intelligent Transportation Systems, vol. 3, no. 1, pp.37-47, March 2002.
    [4] S. Gupte, O. Masoud, R. F. K. Martin, and N. P. Papanikolopoulos, “Detection and classification of vehicles,” IEEE Trans. on Intelligent Transportation Systems, vol. 1, no. 2, pp.119-130, June 2000.
    [5] G. L. Foresti, V. Murino, C. Regazzoni, “Vehicle recognition and tracking from road image sequences,” IEEE Trans. on Vehicular Technology, vol. 48, no. 1, pp.301-318, Jan. 1999.
    [6] J. Wu, X. Zhang, and J. Zhou, “Vehicle detection in static road images with PCA-and- wavelet-based classifier,” 2001 IEEE Intelligent Transportation Systems Conference, pp.740-744, Oakland, C.A., USA, Aug. 25-29, 2001.
    [7] 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, Santorini, Greece, July 2002.
    [8] A. Broggi, P. Cerri, and P. C. Antonello, “Multi-resolution vehicle detection using artificial vision,” 2004 IEEE Intelligent Vehicles Symposium, pp. 310- 314, June 2004.
    [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] C. Tzomakas and W. Seelen, “Vehicle detection in traffic scenes using shadow,” Tech. Rep. 98-06, Institut fur neuroinformatik, Ruhtuniversitat, Bochum, Germany, 1998.
    [11] A. Lakshmi Ratan, W.E.L. Grimson, and W.M. Wells, “Object detection and localization by dynamic template warping,” International Journal of Computer Vision, vol. 36, no. 2, pp.131-148, 2000.
    [12] A. Bensrhair, et al., “Stereo vision-based feature extraction for vehicle detection,” 2002 IEEE Intelligent Vehicles Symposium, vol. 2, pp. 465-470, June 2002.
    [13] T. Aizawa, et al., “Road surface estimation against vehicles’ existence for stereo-based vehicle detection,” IEEE 5th International Conference on Intelligent Transportation Systems, pp. 43-48, Sep. 2002.
    [14] 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.
    [15] D. Guo et al., “Color modeling by spherical influence field in sensing driving environment,” 2000 IEEE Intelligent Vehicles Symposium, pp. 249- 254, Oct. 3-5 2000.
    [16] Y. Ohta, T. Kanade, and T. Sakai, “Color Information for Region Segmentation,” Computer Graphics and Image Processing, vol. 13, pp. 222-241, 1980.
    [17] G. Healey, “Segmenting Images Using Normalized Color,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 22, no. 1 , pp. 64-73, 1992.
    [18] M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis and Machine Vision, London, U. K.: Chapman & Hall, 1993.
    [19] P. Viola and M. J. Jones, “Robust Real-Time Face Detection,” International Journal of Computer Vision, vol. 57, no. 2, pp. 137-154, May 2004.
    [20] E. Osuna, R. Freund, and F. Girosi, “Training support vector machines: an application to face detection,” IEEE Proceeding of Computer Vision and Pattern Recognition, vol. 6, pp.130-136, 1997.
    [21] K.K. Sung and T. Poggio, “Example-Based Learning for View-Based Human Face Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 1, 39-51, 1998.
    [22] R. E. Shapire and Y. Singer, “Improving Boosting Algorithms Using Confidence-rated Predictions,” Machine Learning, vol. 37, no. 3, pp. 297-336, Dec. 1999.
    [23] JULIUS T. Tou, RAFAEL C. GONALEZ, “Pattern Recognition Principles”, Addison-Wesley Publishing Company
    [24] Abjijit S.Pandya, Robert B. Macy, “Pattern Recognition with Neural Networks in C++”, A CRC Book Published in Cooperation with IEEE Press.

    QR CODE
    :::