Clipping

基于meanshift算法的目标跟踪，主要是基于opencv车辆跟踪！！！程序当中进行简单的图像分割(Based on the meanshift algorithm of image segmentation and target tracking.)

数字图像处理有关于图像去雾的新型算法与实现(There are new digital image processing algorithms on the image to go to the fog and Implementation)

通过将三维图像投影成2维ddr图像来实现2D-3D图像配准(By three-dimensional image projection into 2-D images ddr to achieve 2D-3D Image Registration)

任务：用BFS或是DFS对图进行搜索，实现任何拓扑不连通的块的计算，算法要求写在CBFSSearch类中 工程名：Project_BFS 要求：对于生成的任意拓扑，求出其分枝个数，并输出每个分枝的节点 (Task: Using BFS or DFS for searching the graph to achieve any topology unconnected blocks calculation algorithm requires written in CBFSSearch class project name: Project_BFS Requirements: for generating arbitrary topology, find the number of its branches, and output node of each branch)

说明：  使用gpu、cpu并行进行sift算子计算匹配，能够在原来的基础上加速处理，但对显卡要求较高，具体环境配置使用方法可以参照mannual(SiftGPU is an implementation of SIFT [1] for GPU. SiftGPU processes pixels parallely to build Gaussian pyramids and detect DoG Keypoints. Based on GPU list generation[3], SiftGPU then uses a GPU/CPU mixed method to efficiently build compact keypoint lists. Finally keypoints are processed parallely to get their orientations and descriptors. SiftGPU is inspired by Andrea Vedaldi s sift++[2] and Sudipta N Sinha et al s GPU-SIFT[4] . Many parameters of sift++ ( for example, number of octaves, number of DOG levels, edge threshold, etc) are also available in SiftGPU. The shader programs are dynamically generated according to the parameters that user specified. SiftGPU also includes a GPU exhaustive/guided sift matcher SiftMatchGPU. It basically multiplies the descriptor matrix on GPU and find closest feature matches on GPU. Both GLSL and CUDA implementations are provided. )

Retinex理论的基础理论是物体的颜色是由物体对长波（红色）、中波（绿色）、短波（蓝色）光线的反射能力来决定的，而不是由反射光强度的绝对值来决定的，物体的色彩不受光照非均匀性的影响，具有一致性，即retinex是以色感一致性（颜色恒常性）为基础的。不同于传统的线性、非线性的只能增强图像某一类特征的方法，Retinex可以在动态范围压缩、边缘增强和颜色恒常三个方面打到平衡，因此可以对各种不同类型的图像进行自适应的增强。(The basic theory of Retinex theory is the color of the object by object for the long wavelength (red), medium (green), short wave (blue) light reflection ability to decide, rather than by the intensity of reflected light of the absolute value to decide, the color of the object under illumination nonuniformity effects, consistent with the Retinex, that is based on color constancy (color constancy based). Different from the traditional linear, nonlinear image enhancement method of only one kind of features, Retinex can be in dynamic range compression, edge enhancement and three aspects of color constancy hit the balance, thus enhancing adaptive to a variety of different types of images can be.)

SLIC超像素分割matlab版本，主要算法为C++与matlab算法联动(SLIC super pixel segmentation matlab version, the main algorithm is C++ and matlab algorithm linkage)

对两幅图像进行配准，分别提取两幅图像的surf特征点以及描述子，得到粗匹配结果，然后根据粗匹配结果，采用ransac方法计算基础矩阵，并去除误匹配点，得到较准确匹配结果(Two image registration, surf was extracted from the feature points in two images to get the coarse matching and descriptor, then according to the results, the coarse matching results, using RANSAC method to calculate the fundamental matrix, and eliminate the error matching, gain a more accurate matching results)

DDB 图像编程 实现图像的打开，保存，显示，一般处理等功能(DDB image programming to achieve the image open, save, display, general processing and other functions)

基于opencv的相机单目标定程序，很好的学习资源，做图像矫正的可以看看~(Opencv based on a single target of the camera program)