电气工程专业毕业论文中英文资料外文翻译文献CCD双目立体视觉测量系统的理论研究

1、毕业设计（论文）中英文对照资料外文翻译文献电气工程学院（此文档为word格式，下载后您可任意编辑修改！）要求1、外文翻译是毕业设计（论文）的主要内容之一，必须学生 独立完成。2、外文翻译译文内容应与学生的专业或毕业设计（论文）内容相 关，不得少于xxxx印刷符号。3、外文翻译译文用a4纸打印，需包含中文翻译和英文原文。4、年月日等的填写，用阿拉伯数字书写，要符合关于出版物上 数字用法的试行规定，如“2017年5月26日”。5、所有签名必须手写，不得打印。附件：外文原文ccd stereo vision measurement system theoryabstract: using the p

2、rinciples of geometrical imaging ccd stereo vision to build a mathematical model of measurement systems, improve the precision of the system from the start, in theory, focus on system parameters, image recognition errors and the relationship between the precision of the system has in-depth analysis

3、and explore and experiment on the conclusion was verified. research on the actual establishment of this system has a strong guiding role.key words: stereo vision; ccd; measurement accuracy; image recognition; system measurementsintroductionstereoscopic measureme nt in computer vision tech no logy is

4、 an important branch of computer vision has been the focus of the study and the hot spots due to its similar to the human visual system with high precision and speed, and has a simple structure, easy to use, etc., they were widely used in industrial inspection, object recognition, workpiece positi o

5、nin g, robot homing, and many other fields .in recent years many scholars have done a lot of research work 1 - 4. a lot of work which focused on the mathematical model of vision measurement system, the system calibration method 5 - 7 and the target feature point matching algorithm 8 - 9, while the s

6、tructural parameters of the system (of two ccd distanee between the optical axis angle, etc.) are rarely studied. 10 structure parameters of stereoscopic vision corresponding theoretical research, but it is viewing objects from the start of the depth of feeling between the ccd and the object distane

7、e and viewing distance of the two ccd spacing between 3 parameters , did not address the structural parameters of the system measurement accuracy. the practice proved that the structure of the system parameters in practical applications of the system's measurement accuracy is essential. in addit

8、ion, from the stereo vision measurement principle, we can see the error image recognition system accuracy is another important factor in a direct impact. based on the above considerations, the structure from the theoretical parameters of the system and image recognition errors on the precision of th

9、e system of in-depth analysis and research. combination of system parameters on the accuracy of the camera calibration given set of practical applications, stereo vision measurement system design1 binocular stereo vision measurement principle and mathematical modelcamera imaging modelcamera imaging

10、model, the geometric relati on ship between the optical imaging system of mathematics said. at present the application of camera calibration are pinhole camera imaging model imaging model, two-plane model and artificial neural network model. in which a large number of pin hole imaging model is used

11、in an imaging model, which reflects the relationship between an ideal linear map shown in figure 1. one, oc for the camera optical center, oc xcyc zc for the camera coordinate system, oxyz the world coordinate system, oxy for the camera imaging plane physical coordinates.p (x, y, z) for the space of

12、 a material point, p '(x, y) is its projection point on the image plane according to the imaging model, the space object point p (x, y, z) and the relationship between the image point can be expressed asxze y1fr fri ftfr5 fr6 ft2-fl 厲厂9切xyz1-when two or more intersection cameras, you can get 2 i

13、 (i > 2) consisting of equations overdetermined equations, so the least squares method can be used to solve equations to determine the spatial coordinates of object points.1.2 stereo vision measurement system modelbinocular stereo vision system usually consists of two identical ccd structure and

14、properties of the composition and placement of thetwo ccd symmetry. based on the above camera imaging model, from (2) can introduce the following overdeterminedequati ons:厂7 x - fr ny- /厂4 rixr - fr 7 八 fu- fr2ny - fr5m -力3 v - fre rd - /r3 3 -几ft t?x fti - f3 y_/t2 - isy-where r, t, rf, t are the t

15、wo camera coo rd i nate system relative tothe world coordinate system translation and rotation matrix, can be obtained through camera calibration. (x, y), (x y1), respectively, for the space object point (x, y, z) in the two ccd image plane projection of the physical coordinates.0foc(o)figure 2 simp

16、le model of binocular stereo visionin order to analyze structural parameters of the system, where the building shown in figure 2 stereo vision system. in this structure, the coordinate system in the same plane, which for the y axis perpendicular to the paper, the world coordinate system oxyz with th

17、e left camera coordinate origin coincides oc xc yc zc, two camera spacing l, the angle between the two axis 2a. according to the above structure, the camera can determine the composition of the two equations for the overdeterminedxcos a + /sin ajcos ax'cos a - <sin a cos q-xsin a /cos a ysin

18、a-x sin a /cos a-y'sin a0(a)0-/leos a x l sin a -yzsin a-xsin a - /cos a0 xcos a + /an a>-sin a-f >ws al>4 x3 = x sin a /cos a0 x cos a /sin a->?,sin a-f j/cos a-0 'o 0/loos a xzsin avzsin a-by equation (4) yields:_ ad4x3 x y = b o-z2 image recognition errors on the accuracy of t

19、he systemstereo vision system, the space object point in two camera image plane position is represented by pixel coordinates, and pixel area array ccd camera has a certain physical size, which makes the space object point in the image on the real physical coordinates not the exact expression, a fund

20、amental cause of the image recognitionfigure 3. errors.u ximage plane pixel coordinates and physical coordinates thefollowing relations:0丄dx丄dy0voy-1-(5)where: (u, v) the image inpixels coordinate system, dx, dy,respectively, for each pixel in the x-axis and y axis on the physicalsize, (uo, vo) o th

21、e origin of the coordinate system for the oxy oo uvcoordinate system in the coordinates 3. shown in figure 4,assuming that the image recognition accuracy of 0.5 pixel. for a space object point, set the projection to the image plane on the i-line, the first j columns of pixels, then this time the phy

22、sical coordinates of the pointx = (i u0) xdxy =( j - vo) xdyas long as the point falls within the pixel, the coordinate value is a constant. ideally, the coordinates of which should be within a certain range, respectively:(i - u0 0. 5) xdx < x < (i - uo + 0. 5) xdx(j - vo - 0. 5) xdy < y &l

23、t; (i - vo + 0. 5) xdyintegrated on the type, then the error should point to imagerecogniti onex = 0. 5 - ( x - x )ey = 0. 5 - ( y - y )where: x, y, respectively, for x, y rounded. since the existence of image recognition errors, the actual coordinates of image point coordinates and the ideal image

24、point has the following relati on ship: x =? x + ex, y =? y + ey, (x, y) as the point of actual physical coordinates, ( ? x,? y) as the ideal image point of physical coordinates. let the measured object point coordinates p = (a x, a y, a z), by equation (*1) to calculate the projection of the points

25、 in the two cameras the ideal image point coordinates (? x,? y) and (? ? x *,? y)，consider the image recognition error, according to equation (8) come to the actual pixel coordinates (x, y), (x : y')f be substituted into (4), we have been space coordinates of measuring point (x, y, z), the measu

26、rement error of the measured object point can be expressed as ex = x - a x, ey 二丫 - a y, ez = z - a z (9)3 system parameters analysis and experimental results3. 1 structural parameters of the relationship with the precision of the system and mathematical model based on the above derivation process,

27、come to the system structure and system parameters of the relationship between measurement error map. figure 5 is a specific object point measurement error and the camera angle 2a between the two diagrams it can be seen from the figure, ex volatility is notchanging, ey 2a increases with the rising t

28、rend was slow, ez is more violent change, with the increase of 2a increased significantly.i 0.25亠 'l： 0. 20飞0150. io1択 or% 05ki t叫:t15-0.20_0 *25i 一 li 20 406080140 160 1802xal phat 2绘 tfigure 5 the measurement error is a specific spatial point thefigure 6 for a certain object point angle betwee

29、n the two axis graphwithin the coordinate origin with the world average measurement error and the two cameras and two camera angle 2a between the distance between the l map. it can be seen, when a certain distanee between the two cameras, the average error with the increase of 2a, when the angle bet

30、ween the two cameras is fixed, the average error increases with the distance in creasing.figure 6 average error and the angle between two axes, the distance between the two cameras chartoverall, structural parameters and precision of the system is a more complex function can be summarized as follows

31、:1) spacing between the camera and the measurement error is directly proportional to the smaller distance, the smaller the error;2) when the camera is not greater than the angle between the 130 °, the measurement error is small, whereas larger. has high credibility. 3. 2 structural parameters o

32、n the accuracy of camera calibrationin practice, the need to create two links between ccd coordinates, which need to be two-dimensional ccd calibration, in order to obtain the rotation between the two ccd matrix and translation matrix. proved the precision of camera calibration parameters and system

33、 structure also has a very close relationship calibration method uses a template based on single-plane calibration strategy, the accuracy was assessed using an assessment based on the length of the checkerboard method the method also can be used as measurement error of the measurement method. calibr

34、ation template of 10 to 50 mm length of the checkerboard was repeated experimental results shown in tabletable 1 structure parameters on the average error of calibration.y /（a）li nun15406590no2000.085 00.094 l0.136 40.193 30.282 03000.151 50.170 l0.231 40.276 90.356 l4000.272 9030 30.376 50.456 40.7

35、60 35000.446 l0.642 20.713 00.92i 8i.279 26000.521 80.702 30.912 41.050i.467 las can be seen from table 1, when the camera a certain distance, the calibration error increases with the optical axis angle increasing when the angle between the fixed axis, the camera calibration error with increasi ng d

36、istance increases. experimental results dem on strate that when the distanee between the two cameras is not more than 500mm, two-axis angle of not more than 60 °, the calibration error is small.4 conclusionintegrated system parameters on the measurement accuracy and precision of calibration, st

37、ereo vision system in the establishment of the two camera optical axis angle and distanee between the two cameras should be as small as possible, but in practice, taking into account the ease of visual target feature point matchi ng , especially for large-scale real-time moving object tracking, a ta

38、rget is obscured happens, the angle between the two camera optical axis should be chosen between 30 ° 60 ° in addition, the target feature point image recognition accuracy to achieve sub-pixel accuracy as possible, try to avoid the "loss of good as a mile'* phenomen on. according

39、to the above set up a stereo vision system is derived, and achieved good experime ntal results show that the con elusions of this paper has great practical significance, for further in-depth study has laid a solid foundati on.附件：外文资料翻译译文ccd双目立体视觉测量系统的理论研究摘要：利用几何成像原理建立起ccd双目立体视觉测量系统的数学 模型，从提高系统测量精度出发

40、，在理论上重点对系统结构参数、图像 识别误差与系统测量精度的关系进行了深入的分析和探讨，并通过实验 对结论进行了验证。研究内容对实际建立该测量系统具有很强的指导作 用。关键词：立体视觉；ccd ; 测量精度；图像识别；系统 测量 引言双目立体视觉测量技术是计算机视觉中的一个重要分支，一直是计 算机视觉研究的重点和热点之一。由于其近似于人眼视觉系统，具有较 高的测量精度和速度，并具有结构简单，便于使用等优点，所以被广泛 应用于工业检测、物体识别、工件定位、机器人自导引等诸多领域。 近年来许多学者对此进行了大量的研究工作1-4。其中大量的工作集 中在对视觉测量系统的数学模型、系统的定标方法5-7以

41、及目标特征 点匹配算法8-9的研究上，而对系统的结构参数（两个ccd之间的距 离、光轴夹角等）研究得却很少。文献10对立体视觉结构参数进行了 相应的理论研究，但它是从观看物体时的深度感出发研究ccd与物体 之间的距离、两个ccd间距和观看距离3个参数之间的关系，没有涉 及到结构参数对系统测量精度的影响。而实践证明系统的结构参数设置 在实际应用中对于系统的测量精度是至关重要的。此外，从立体视觉测 量原理中，可以看出图像识别误差是另一个对系统测量精度产生直接影 响的重要因素。综合以上考虑，从理论上对系统的结构参数设置和图像 识别误差对系统测量精度的影响进行了深入的分析和研究。结合系统结 构参数对摄

42、像机定标精度的影响，给出了实际应用中组建双冃立体视觉 测量系统的设计方案。1双目立体视觉测量原理及数学模型1.1 摄像机成像模型摄像机的成像模型，是光学成像系统几何关系的数学表示。目前在摄 像机标定中应用的摄像机成像模型主要有针孔成像模型、双平面模型 和人工神经网络模型等。其中针孔成像模型是目前大量采用的一种成像 模型，它反映的是一种理想的线性映射关系，如图1所示。其中，oc为摄 像机的光心，oc xcyc zc为摄像机坐标系，oxyz为世界坐标系，oxy 为摄像机成像平面物理坐标系。p( x , y , z)为空间一物点,p ( x , y)是其在图像平面上的投影点。根据该成像模型,空间物点

43、p(x,y,z)与像点之间的关系可表示为x fr fr2 jh ftzc 尹=和4 fr5 /厂6 ftl-i l 77 心厂9 ty xyz-1-当两个或两个以上摄像机进行交会时，可以得到2i(i 2 2)个方程 所组成的超定方程组，因此可以用最小二乘法对方程组求解以确定空间 物点的坐标。1.2双目立体视觉测量系统的数学模型双目立体视觉系统通常由两台结构和性能完全相同的ccd组成， 并且两个ccd摆放位置对称。基于上述摄像机成像模型，由式(2)可以 推出如下超定方程组：；7 x -力】igx -,/hny -ny -fv y -力6rx-ai-/r2，r ryx-/r3'!-fu&#

44、39;!3-介5'f3-a&ft 1-/3jh - t3y/tl- t3x'_/t2 -其中r,t9r, , t分别为两摄像机坐标系相对于世界坐标系的平移和旋转矩阵，可以通过摄像机标定得到o(x,y),(x,y)分别为空间物点(x , y , z)在两ccd图像平面的投影的物理坐标。图2 双目立体视觉简易模型为了对系统结构参数进行分析,这里构建如图2所示的立体视觉系 统。在该结构中，三坐标系处于同一平面内，其中y轴垂直纸面向里，世 界坐标系oxyz与左摄像机坐标系oc xc yc zc原点重合俩摄像机间 距为l,两光轴夹角为2a。根据上述结构，可以确定两摄像机组成的超

45、定方程组为xsin a /cos a 0 ysin a- fx 'sin a - /cos a 0 ”sin q- f 00-/leos a - x l sin尹cos ax cos a - /sin ay cos a-(a)-yfl sin axsin q -vsin q_ */cos ad4 x3 =-x sin q-/cos a-j/sin a000 xcos a + /sin a-f ycos a0 xzcos q - /'sin a -f yfcos a-/leos a - x l sin al - vrl sin a则由式可得:ad4x3 x y-z2图像识别误差对

46、系统测量精度的影响立体视觉系统中，空间物点在两个摄像机图像平面上的位置是通 过像素坐标来表示的，而面阵ccd摄像机像素具有一定的物理尺寸， 这就使得空间物点在图像上的真实物理坐标无法得到准确的表达，从根本上造成了图像识别误差。如图3所示。o.(% vj图像平面上像素坐标系与物理坐标系有如下关系:丄audx °xv-1-0 t voy-1-0 0 1 -(5)其中：(u , v)是以像素为单位的图像坐标系的坐标,dx , dy分别为每一个像素在x轴和y轴方向上的物理尺寸，(uo , vo)为oxy坐标系原点o在oouv坐标系中的坐标3。如图4所示，假设图像识别精度达到0. 5个像素级。对于一空间物点,设其投影到图像平面上的第i行，第j列的像素中，则此时该点的物理坐标为x = (i - uo) xdxy =(jvo) xdy即只要该点落在该像素内,其坐标值是一个定值。而理想情况下的坐标应分别在一定的范围内：(i - uo 0. 5) xdx < x < (i - uo + 0. 5) xdx(j - vo - 0. 5) xdy < y v (i v0 + 0. 5) xdy综合上式，则对应该点的图像识别误差为ex = 0. 5 - ( x - x )ey = 0. 5 - ( y - y )其中：