fa0d

本文针对多光谱图像配准中不同光谱图像间存在较大的灰度差异、同一景物在不同波段表现的特征也各不相同等问题，提出了基于互信息相似性测度的多光谱图像配准算法。(In this paper, multi-spectral image registration between different spectral image there is a big difference in gray scale, the same scene in different bands performance characteristics are different questions, we present a similarity measure based on mutual information of multi-spectral image registration algorithm .)

原创基于c++语言编程实现了MC算法在三维图像处理中的应用，以及有许多二维图像到三维图像表面的重建过程算法。通过VC2008，编译已通过。(I have realized MC algorithm about the application of processing 3-D image based on C++ language also realised the technology on image surface reconstruction from 2-D to 3-D image.They are all compiled successfully using VS2008)

1.本程序功能包含显示直方图，OTSU的单值分割，OTSU的二值分割,OTSU的三值分割 2.在OTSU的分割时，通常情况下我们是通过类间方差得到一个分割阈值，但是有时候我们需要得到各灰度级别的目标，那么采取多值分割是 很必要的，通过改进得到OTSU的多值分割方法 3.本程序另外还有显示直方图，计算程序运行时间，处理结果以新的窗口显示等细节，这部分适合MFC初学者。(1. This procedure shows the histogram feature, OTSU single segmentation, OTSU binary segmentation, OTSU three segmentation 2. OTSU segmentation, it is usually the case we are through the between-cluster variance by a partition threshold , but sometimes we need to be the gray level of the target, then the multi-segmentation is necessary, through improved access to multi-OTSU segmentation methods 3. This procedure in addition to show the histogram to calculate run time, treatment the results of a new window display the details of this part of MFC for beginners.)

分类程序的实现，可在vc++平台中运行，方便大家对算法的熟悉与学习(Classification procedures to achieve, can be run in vc++ platform to facilitate learning of the algorithm are familiar with)

一种基于non-sample的纹理合成demo，程序性能还有待优化，效果还不错.(texture synthesis demo.)

halcon图像处理软件用来检检测图像的圆状物体。可直接使用。 (halcon image processing software is used to check the oblong object detection image. Can be used directly.)

Source code to segment skin colour.

采用了Harrtraining和离子滤波算法实现了拥挤人群人头计数，非常有用。VC++和Opencv开发，采用Oepncv中的Harrtraining训练一个分类器即可运行(Human detection and tracking in high density crowds is an unsolved problem. Standard preprocessing techniques such as background modeling fail when most of the scene is in motion. We integrate human detection and tracking into a single framework, and in- troduce a conrmation-by-classication method to estimate condence in a tracked trajectory, track humans through occlusions, and eliminate false positive detections.)

多径条件下基于加权空间平滑的阵元幅相误差校正(Multipath based on weighted spatial smoothing array element amplitude and phase error correction)

基于opencv的Kinect深度图像的去噪，滤波(Opencv based Kinect depth image denoising, filtering)