The Recovery of Reference Plane of Objects using a Dual-CCD Image System 張家維、紀華偉
E-mail: [email protected]
ABSTRACT
Imagine recognition technique plays an important role in industrial automation. Spatial information recovering from 2D images is one of key element of imagine processing technique. This study develops a method based on the parity of two images to recover the 3D information of an object from 2D images. First, the 2D information of the characteristic points of left and right images is extracted from, then the 3D information of these characteristic points is recovered using the method developed in this study and the parameters of the CCD system. These points’ 3D information is then used to construct a reference plane by using the least square method and Newton’s method. Three examples are given to demonstrate the feasibility of the proposed method. The real positions of the object are known. The comparison results show that the proposed method can recover the object’s 3D information. The error of normal vector and the mid-point coordination of the reference plane calculated from the recovered 3D information are within the acceptable range.
Keywords : Disparity ; Least square Method ; Stereo vision ; Newton’s Method Table of Contents
目錄 封面內頁 簽名頁 授權書 iii 中文摘要 iv 英文摘要 v 誌謝 vi 目錄 vii 圖目錄 x 表目錄 xiii 第一章 緒論 1.1 前言 1 1.2 研究 動機及目的 2 1.3 研究方法 3 1.4 論文架構 3 第二章 影像原理 2.1 影像色彩理論 5 2.2 影像處理 6 2.2.1影像擷取 8 2.2.2影像 追蹤 9 2.2.3清楚化 9 2.2.4判斷形狀 13 2.3 立體影像之原理與影像重疊百分比 13 2.4 影像對應面臨問題 15 第三章 CCD架設 與空間座標計算 3.1 二維與三維關係 17 3.2 雙影像CCD空間系統架設分類 18 3.3 點資訊判別 22 3.3.1二維點資訊判別 22 3.3.2點資訊在立體影像的對應 24 3.4 建立雙影像CCD空間系統 25 3.5 座標系統轉換 27 3.5.1 平移轉換 29 3.5.2 旋轉轉換 30 第四章 空間建立及影像資訊擷取 4.1 空間建立 34 4.1.1空間容許誤差 36 4.1.2建立最佳空間 53 4.1.3雙CCD鏡頭與世界座標 之關係 54 4.2 影像資訊擷取 55 4.2.1影像資訊兩點對N點 55 4.2.2影像資訊三點對N點 56 4.2.3影像資訊四點對N點 58 第五章 實驗分析與計算 5.1 CCD鏡頭參數測定 60 5.1.1驗證擷取晶片實際大小及有效畫素 60 5.1.2推算利於本文觀察之鏡頭焦距 62 5.1.3 CCD鏡頭架設置CNC機台空間座標定位 64 5.2 牛頓法 66 5.3 實驗步驟 67 5.4 實驗驗證 68 第六章 結論 6.1 結論 79 6.2 建議與未來展望 80 參考文獻 82
REFERENCES
參考文獻 [1] 余松煜、周源華、吳時光，數位影像處理，儒林圖 書，台北；1993。
[2] 楊武智，影像處理與辨認，全華科技圖書；1996。
[3] T. Uchiyama and M. A. Arbib, “Color image segmentation using competitive learning”, IEEE Trans. on Pattern Anal. Machine Intell, Vol.
16, pp. 1197-1206, 1994.
[4] E. Littmann and H. Ritter, “Adaptive color segmentation – A comparison of neural and statistical methods,” IEEE Trans. On Neural Networks, Vol. 8, Jan. 1997.
[5] H. -D. Cheng, Y. Sun, “A hierarchical approach to color image segmentation using homogeneity,” IEEE Trans. on Image Processing, Vol.
9, No. 12,pp.2071-2082, 2000.
[6] N. Vandenbroucke, L. Macaire, J. -G. Postaire, “Color image segmentation bypixel classification in an adapted hybrid color space.
Application to soccer image analysis,” Computer Vision and Image Understanding, Vol. 90, pp. 190-216, 2003.
[7] A. Dumitras and A. N. Venetsanopoulos, “Angular map-driven snakes with application to object shape description in color images,” IEEE Trans. on Image Processing, Vol. 10, No. 12, pp. 1851-1859, 2001.
[8] Y. T. Wu, L. -F. Chen, H. Y. Chen, P. L. Lee, T. C. Yeh, J. -C. Hsieh, “Awavelet-based approach for color image registration,” J. Imaging Science and Technology, Vol. 47, No. 3, pp. 185-199, 2003.
[9] F. -H. Cheng, W. -H. Hsu, T. -W. Chen,“Recoveringcolors in an image with chromatic illuminant,” IEEE Trans. on Image Processing, Vol.
7, No. 11, pp.1524-1533, 1998.
[10] H.Altunbasak and J. Trussell, “Colorimetric restoration of digital images,” IEEE Trans. On Image Processing, Vol. 10, No. 3, pp. 393-402, 2001.
[11] J. F. C. Wanderley and M. H. Fisher, “Multiscale color invariants based on the human visual system,” IEEE Trans. on Image Processing, Vol.10, No. 11, pp.1630-1638, 2001.
[12] Varady T. Martin R R and Cox J, “Reverse engineering of geometric models – an introduction”,Computer Aided Design, Vol.29 n.4 pt0, pp.225-268,1997.
[13] Williams, J.A.; Bennamoun, M.; Latham, S（1999）”Multiple view 3Dregistration: a reviewand a new technique Systems, Man, and Cybernetics”,in.- 72 -IEEE Conf. , Volume:3 , p497 -502 [14] Yamany, S.M.; Farag, A.A （1999）, “Free-form surface registration using surfacesignatures”,Computer Vision, The Proc.IEEE Conf. , Volume: 2 , p.1098 –1104 [15] Lisa, G Brown,（1992）“A Survey of Image Registration Techniques”, ACMComputing Survey. Vol 24, No. 4, p.325-376 [16] Goshtasby, A. (1988) “Image Registration by local approxmation “,Image VisionComputing Vol.6,No.4,p.255-261 [17] Wolberg, G. (1990)”Digital Image Warping”, IEEE. Computer Society Press, LosAlamitos. Calif.applications,” D. Reidel PublishingCompany, 1987.
[18] Lew, M.S., Huang, T.S., Wong, K.W., “Learning and feature selection in stereo matching,” IEEE Transactions on Pattern Analysis and Machine Intelligence , Vol. 16, No.9, pp.869-881, 1994.
[19] Gonzalez R. C. and Woods R. E., "Digital Image Processing, 2nd ed.",Prentice-Hall, 2002 [20] P.J.M Aarts and Van Laarhoven；
”Simulated annealing and applications: Mathematics and its [21] Gonzalez , R. C., and Woods, R. E., “Digital Image Processing,” Addison Wesley, United States of America, 1993.
[22] Vishvjit S. Nalwa, ” A Guided Tour of Computer Vision,” Addison-Wesley Publishing Company,1993.
