222171720920061213101744868886

本程序使用dcmtk库，可以显示大部分的DICOM图像。非压缩、压缩黑白图像以766灰阶显示，彩色图像正常显示。 对于初用dcmtk库的开发者来说，入门较难，本程序已使用VC6工程将主要库加入工程中，可以参考本工程的设置。另外，对于高于8位的黑白图像，本程序也提供一个处理方法的参考。(This procedure used dcmtk library, you can see that the majority of the DICOM image. Non-compressed, compressed to 766 gray-scale black-and-white images show that color image display. Dcmtk library used for the early developers, the entry more difficult, the procedure has been in use for the main library VC6 project will join the project, can refer to the project settings. In addition, higher than the 8-bit black-and-white images, the program also provides a reference method.)

Opencv处理图像，用ostu法实现图像的二值化(Opencv image processing, using ostu method to achieve image binarization)

基于SUFT的特征提取与匹配，内涵详细的文档说明，很好的实现了特征提取与匹配，该方法较基本的SIFT有很大的提高(Extraction and matching of features based on SUFT, detailed content of the documentation, very good realization of the feature extraction and matching, SIFT the method is basic is greatly improved)

该算法可以应用于计算机视觉的物体识别以及3D重构中。(The algorithm can be applied to object recognition in computer vision and 3D Reconstruction.)

行人检测HOG+SVM进行图片中行人检测，提供训练用的pos和neg样本，效果还可以；没有SVM工具箱的，压缩包里已经提供了，安装一下即可(Pedestrian detection HOG + SVM for pedestrian detection in pictures, providing POS and neg samples for training, the effect is good; without SVM toolbox, the compression package has been provided, just install it.)

基于meanshift算法的目标跟踪，主要是基于opencv车辆跟踪！！！程序当中进行简单的图像分割(Based on the meanshift algorithm of image segmentation and target tracking.)

BMP图像边缘提取后 根据边缘点集直线拟合(BMP image edge extraction fitting a straight line)

有关彩色图像分割与复杂场景下目标跟踪方法研究的一篇博士论文(On the color image segmentation and complexity of the scene target tracking methods under study for a Ph D thesis)

说明：  使用gpu、cpu并行进行sift算子计算匹配，能够在原来的基础上加速处理，但对显卡要求较高，具体环境配置使用方法可以参照mannual(SiftGPU is an implementation of SIFT [1] for GPU. SiftGPU processes pixels parallely to build Gaussian pyramids and detect DoG Keypoints. Based on GPU list generation[3], SiftGPU then uses a GPU/CPU mixed method to efficiently build compact keypoint lists. Finally keypoints are processed parallely to get their orientations and descriptors. SiftGPU is inspired by Andrea Vedaldi s sift++[2] and Sudipta N Sinha et al s GPU-SIFT[4] . Many parameters of sift++ ( for example, number of octaves, number of DOG levels, edge threshold, etc) are also available in SiftGPU. The shader programs are dynamically generated according to the parameters that user specified. SiftGPU also includes a GPU exhaustive/guided sift matcher SiftMatchGPU. It basically multiplies the descriptor matrix on GPU and find closest feature matches on GPU. Both GLSL and CUDA implementations are provided. )

ORB和FREAK局部特征对比实验ORB_FREAK(ORB and FREAK local features of comparative experiments ORB_FREAK)