fbmpCP

利用K均值聚类的方法实现人体的检测，混合高斯模型建立背景并实时更新(The use of K-means clustering method to achieve the human body detection, Gaussian mixture model to establish the background and real-time updates)

该程序初始时使用背景差分法自动检测目标，当目标完全进入图像中后，改用meanshift方法对目标进行跟踪。(the program use background subtraction to detect the target first,when the target fully enter the screen,change to meanshift method to track the target.)

约束最小二乘法图像复原代码，直接上图片就可以使用的。(Constrained least squares image restoration code directly on the image to be used.)

对立体视觉的双目图像进行极线校正，以实现双目致密匹配(Of three-dimensional visual image of the binocular epipolar rectification to realize dense binocular matching)

用matlab实现levelset水平集分割图像！(levelset to fen ge Image ag dag gf a ga ga h agr d we v g)

该文件使用特征点提取-图像匹配-图像剪影三部，精确检测车辆或运动物体。(the documents Feature Extraction-Image Matching- Image Capture 3, accurate detection of vehicles or moving objects.)

基于MRF的SAR图像分割，在空域下进行建模，对初学者很有帮助。(SAR image segmentation based on MRF modeling in airspace, useful for beginners.)

说明：  《视觉SLAM十四讲》高翔，完整版，前10章。对视觉定位，机器学习，深度学习有很大帮助(Gao Xiang, the complete version of vision slam 14 lectures, is very helpful for vision positioning, machine learning and deep learning)

图形图像处理中的平滑处理，可以实现部分的功能，但是还可以继续完善(Graphic image processing smoothing, can achieve some of the functions, but can also continue to improve)

基于区域方差取大的图像融合算法 代码编写经典(Based on the regional variance max of the image fusion algorithm )