L0Smoothing

STM32F103开发板，HC-SRO4超声波测距模块

Image Matching Fundamentals Method Document PDF Files Slide2

说明：  解决一些图像处理的小问题，具体的划分和问题，文件里有提到(Solve some small problems in image processing)

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.)

超宽带雷达信号二维FFT求速度和距离，速度补偿后的算法(Ultra-wideband radar signal 2D FFT for speed and distance, speed compensated algorithm)

实现了三维超声PNN算法的GPU加速；实现GPU加速的CT圆轨道平板探测器FDK重建算法；提供对canny边缘检测算法的支持；提供交互式graph cut分割方法；实现OSTU分割算法；(Three dimensional ultrasound PNN algorithm GPU acceleration to achieve GPU accelerated CT reconstruction algorithm for circular orbits FDK flat panel detector provide support for canny edge detection algorithm provide interactive graph cut segmentation achieve OSTU segmentation )

说明：  提取纹理图像特征，包括平均值、标准差、平滑度、三阶矩、一致性、和熵。(Extract texture features, including mean, standard deviation, smoothness, third moment, consistency, and entropy.)

说明：  都是各向异性扩散用于图像去噪的文章，中文文献，看起来比较方便(Are anisotropic diffusion for image denoising article, Chinese literature, it seems more convenient)

说明：  按照最邻近原则把待分类样本点分到各个簇。然后按平均法重新计算各个簇的质心，从而确定新的簇心。一直迭代，直到簇心的移动距离小于某个给定的值。(According to the nearest neighbor principle, the sample points to be classified are divided into clusters. Then the centroid of each cluster is recalculated according to the average method to determine the new cluster center. Iterate until the moving distance of the cluster center is less than a given value)

利用V4L2协议进行图像处理的编程框架结构(The utilization the V4L2 protocol for image processing programming framework structure)