BilateralFiltering

用恒虚警算法CFAR实现海面sar图像目标检测的matlab代码(With the constant false alarm algorithm CFAR implementation to the surface of the SAR image target detection of matlab code )

说明：  用c写的jpg编解码，包括jpeg2bmp和bmp2jpeg，可在vc6下调试。(With c written jpg codec, including jpeg2bmp and bmp2jpeg, may be under vc6 debugger.)

该源程序实现了SAR图像变化检测的功能，方法是基于修正马尔科夫随机场的模糊C均值实现SAR图像的变化检测。(The source program realizes the function of SAR image change detection. The method is based on modified Markov random field fuzzy C-means to realize SAR image change detection.)

说明：  本代码总结了信息熵、条件信息熵、PSNR、SSIM等图像评价指标(This code summarizes information entropy, conditional information entropy, PSNR, SSIM and other image evaluation indexes)

使用Tensoflow实现图卷积神经网络模型(Use Tensoflow Implementation Figure convolution neural network model)

通过对彩色图像的处理，来计算某一个区域的面积。(The color image processing to calculate the area of ​ ​ a region.)

根据图的邻接矩阵判断图的连通性并计算图的分块数(To determine the connectivity of the graph and computing graph blocks according to the adjacency matrix)

图像超分辨率是指从一序列低分辨率观测图像中重建高分辨率图像。图像超分辨率充分利用了各帧图像 间相似而又不同的信息。(Compared with the model derived from Kolmogorov spectrum, the new model introduces more complete transcendent constraints and is more similar to the physical characteristics of atmospheric turbulence.)

说明：  图像分割，还可以，kmeans聚类的方法。k-means算法是一种聚类算法，所谓聚类，即根据相似性原则，将具有较高相似度的数据对象划分至同一类簇，将具有较高相异度的数据对象划分至不同类簇。(K-means algorithm is a clustering algorithm. The so-called clustering is to divide data objects with high similarity into the same class cluster and data objects with high dissimilarity into different class clusters according to the similarity principle.)

说明：  实现 %1、利用RGB模型识别天空区域；2、利用边缘识别检测天空边缘分割线；3、利用预测边缘点和实际边缘点的周围区域的均值滤波与本边缘点下方的像素之间的差异大小来修正天空边缘分割线 %4、将sky_seg+depthmap_v2中多余的带注释的地方删掉了 %！！！记得在295行，一定要改动是用I6还是I7，如果用sky_initia(f = edge(double(BW),'canny',thresh,sigma);)