After analyzing plane measurement detailedly , we know that the precision of measurement is decided by the precision of the homography between the image and the scenic plane . in the following chapter , several algorithms used to solve homography matrix are discussed 在分析了平面测量的基础上，我们知道测量的精度取决于图象平面和世界平面之间单应的精度，因此接下来论文花了大量的篇幅来讨论单应矩阵的各种算法。
At the beginning , the basic theory of plane measurement ? some basic elements in planar projective geometry , including 2d protective plane , homogeneous coordinates and homography are introduced . the pinhole camera model and the basic algorithm of image measurement are discussed 首先介绍了平面测量问题的理论基础? ?平面射影几何的一些基本元素：射影平面，齐次坐标，平面单应等，接着讨论了摄象机针孔模型以及基于图象的平面测量基本原理。
The research on plane measurement and homography has many other applications , such as rectifying images , registering image sequences , etc . image rectification can resume the true geometric figure of the object by removing the projective distortion from images 平面测量以及平面单应问题的研究还有很多其他的应用，如矫正图象的射影失真、实现旋转图象序列的整合等等。图象射影失真的矫正技术较圆满地消除了图象的射影失真，恢复了物体的真实几何形状。
The equations derived are more complicated if more precise model is employed for high accuracy . the technique , which does n ' t need to have an explicit model - calibration based on neural networks implicit vision model , is more effective . since bp neural network can implement any nonlinear relationship from input to output and need n ' t to model , and the classical stereo vision approach based on explicit model are very complicated , an algorithm of stereo vision based on bp neural networks implicit vision model is proposed 利用神经网络可以充分逼近任意的非线性关系且无须精确建模的特点，针对传统的立体视觉方法过程繁琐，对安装精度要求高的不足，本文提出了一种基于bp神经网络隐式视觉模型的立体视觉方法，该算法实施起来比较简便；针对已有的像差修正算法计算过程复杂的不足，提出了一种基于bp神经网络的修正成像误差的算法；针对具有共面特征的点的三维重构的应用，提出了一种基于径向基函数网络的二维平面测量算法。
After the discussion of the plane measurement , we continue the discussion about the important method of the stereo measurement , such as : the method of resolving the fundamental matrix , the method of recovering the fundamental matrix from the camera matrix , the method of recovering the 3d point based on the trigonometry 在平面测量理论的基础上，论文继续讨论了基于图像的立体测量的重要方法? ?两视图立体重构。详细研究了其中基本矩阵的算法、由基本矩阵恢复摄像机矩阵的算法、三角法恢复空间点的算法等，在这之后给出了真实试验结果。
