input_ML

计算单应矩阵，输入为2D图像坐标点和3D世界坐标点，输出为3x3单应矩阵(Calculate homography)

说明：  shepp-logan的2D直接傅里叶反变换法(Shepp-logan 2-D Direct Fourier Inverse Transform Method)

说明：  二代提升法实现的haar小波变换程序 及整数小波变换。haar小波实现(Method II upgrade the haar wavelet transform procedures and integral wavelet transform. Haar Wavelets)

图像的SNR，PSNR以及MSE的计算源代码(The image SNR, PSNR and the source code for the calculation of MSE)

三维重建是指对三维物体建立适合计算机表示和处理的数学模型,是在计算机环境下对其进行处理、操作和分析其性质的基础,也是在计算机中建立表达客观世界的虚拟现实的关键技术。(Three-dimensional reconstruction refers to the establishment of a mathematical model suitable for computer representation and processing of three-dimensional objects. It is the basis for processing, manipulating and analyzing their properties in the computer environment. It is also the key technology for establishing a virtual reality to express the objective world in the computer.)

2D转3D中的深度图生成模块，内部有图片例子。(depth map generation module, 2D to 3D)

三维图形的正轴测图，正视图，侧视图，俯视图的绘制(3D isometric map is the address map, side view overlooking Map)

c 实现了以点阵表示的多边形的最小外接矩形，并求出其的面积。(c to achieve a in order to dot-matrix expressed of polygons of the minimum bounding rectangle, and calculated its of the area.)

改进的帧间差法运动目标追踪算法,比以前的经典算法有改善，不会出现边框锁定到边远的情况(Improved inter-frame difference method moving target tracking algorithm)

说明：  非刚性三维重建实例代码，源自一篇IEEE论文。(Non-Rigid SFM code from an IEEE paper.)