LRTsigma

阴影去除，用于视频监控中的运动目标检测后提取运动目标(Shadow Removal for moving object detection in video surveillance Moving Target Extraction)

基于HOG的行人检测，作者的源代码有错误，现代码已经进行了改变，并可以调试通(Histograms of Oriented Gradients for Human Detection, the writer s code has some errors, and I have correct the errors, and the code is right under C++ buidler)

说明：  最大熵双阈值分割算法，基于遗传算法优化的快速最大熵双阈值分割算法。(Maximum Entropy Double Threshold Segmentation and Fast Maximum Entropy Double Threshold Segmentation Based on Genetic Algorithms.)

fy3（hdf5格式）mersi数据投影到等经纬度(projecting fy3 mersi hdf5 format to longlat )

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.)

matlab图像处理，可以提取图像轮廓，提取效果好。(matlab image processing, image contour can be extracted, extraction effect.)

通过遗传算法选择道路图象分割的最佳阈值,阈值的选择采用最大类间方差的办法,程序运行结果达到相当理想的效果(Through the genetic algorithm to choose the best road image segmentation threshold, the threshold was chosen as the maximum between-cluster variance approach, the program results achieved the desired results rather)

说明：  通过检测二维小波变换的模极大值点可以确定图像的边缘点，利用小波变换的多尺度性用于图像的边缘检测(By detecting modulus maxima point of two-dimensional wavelet transform we can determine the image edge points, using multi-scale nature of wavelet transform in image edge detection)

YUV420视频的缩放，经过高度的优化，其中三次卷积插值（cubic convolution）算法的效果最好，优化程度也最高。其基本思想是通过整型化、查表等方法消除每一帧图像插值运算中的浮点运算和乘除法运算。(scale YUV420 video frames with cubic, bilinear & cubic convolution interpolation algorithms。)

用FCM 对自然图像 sar图像以及纹理图像进行快速分割 ，用一维和二维直方图分别对图像进行特征映射 从而快速的对图像进行分割 包含结果截图 (By FCM sar image of natural images quickly and texture image segmentation, with one-dimensional and two-dimensional histogram of the image feature maps were so fast image segmentation screenshot contains the results)