saliency_SR

图像处理方面，包括滑动窗口，线性滤波，中值滤波(Image processing, including sliding window, linear filtering, median filtering)

这是一个用于血管分割的程序，程序中附带多幅测试图片(This is a program for vascular segmentation, with multiple test images attached to the program)

光流法，经典的LKPR-marzat算法，适合研究光流法的学者使用，可执行，无错误 (Optical flow method, the classic LKPR-marzat algorithm, for research scholars to use optical flow method, executable, error-free)

用delaunay三角剖分和网格填充对离散点云数据进行网格重建(Mesh reconstruction of discrete point cloud data using Delaunay triangulation and mesh filling)

通过执行程序，可以实现对物体视差图的生成，进而可以实现深度图。(Through the implementation of the program, you can achieve the object disparity map, and then you can achieve depth map.)

基于离散余弦变换的水印程序，大家看看有没有可以改进的地方(Discrete cosine transform-based watermarking process, everyone can see if there is any improvement)

利用radon变换进行图像倾斜矫正的算法代码实现(Using radon transform algorithm for image tilt correction code)

三维激光点云配准是点云三维建模的关键问题之一。经典的 ICP 算法对点云初始位置要求较高且配准 效率较低，提出了一种改进的 ICP 点云配准算法。该算法首先利用主成分分析法实现点云的初始配准，获得较好 的点云初始位置，然后在经典 ICP 算法的基础上，采用 k － d tree 结构实现加速搜索，并利用方向向量夹角阈值去除 错误点对，提高算法的效率。实验表明，本算法流程在保证配准精度的前提下，显著提高了配准效率。 (Three-dimensional laser point cloud registration is one of the key three-dimensional point cloud model. High classical ICP algorithm to the initial position of the point cloud registration requirements and low efficiency, proposed an improved ICP point cloud registration algorithm. Firstly, the use of principal component analysis of the initial point cloud registration, get a better initial position of the point cloud, then the basis of classical ICP algorithm using k- d tree structure to achieve speed up the search, and using the direction vector angle the removal of the threshold point error and improve the efficiency of the algorithm. Experiments show that the algorithm processes to ensure the accuracy of registration under the premise, significantly improve the efficiency of registration.)

说明：  SIFT的MATLAB源码，由加州大学的一位博士编写。(SIFT the MATLAB source code, from the University of California, prepared by Dr. A.)

这是一个sar成像的算法，它融合了cfar的处理，使目标更加凸显。非常适合用于sar成像和cfar算法的研究。(This is a sar imaging algorithm, which combines cfar processing, the target is more prominent. Very suitable for research sar algorithm for imaging and cfar.)