demons

一个很好类子来说明类模板的使用，可以比较明了类模板的使用方法，最好进行单步调试(use of class template )

使用GDAL库，用于遥感影像的特征点提取(Using the GDAL library, used for remote sensing image feature point extraction)

说明：  这是一个用C++语言实现一个指纹识别程序，要求满足FVC国际竞赛标准，并在学校建立的指纹库上实测。程序里应用到的技术有：中值滤波、直方图均衡化、脊线方向提取、Gabor滤波、指纹细化、特征提取、特征点过滤、基于局部特征点的特征匹配(This is a C++ Language realization of a fingerprint identification procedure, the requirements FVC meet international competition standards, and established in the school library on the measured fingerprint. Program applied to the technology are as follows: median filter, histogram equalization, the direction of the ridge line extraction, Gabor filtering, fingerprint thinning, feature extraction, feature point filtering, based on local feature points of the feature matching)

基于最小二乘法的相位解缠VC++算法 (least squares method based on the VC Phase Unwrapping Algorithms)

VTK读取BMP序列图片实现MC算法面绘制，并且将绘制结果保存为STL格式。(VTK read BMP image sequences to achieve MC surface rendering algorithm, and the results will be drawn saved as STL format.)

基于样本的纹理合成加速方法，MRF，基于Li-Yi Wei的论文。(Acceleration method based on texture synthesis samples, MRF, based on Li-Yi Wei of paper.)

该代码，利用GDAL 1.4.2库实现遥感图像的几何校正、图像配准等，vs 2010实现。(The code GDAL 1.4.2 library implementation of remote sensing image geometric correction, image registration, vs 2010.)

针对粒子概率假设密度(PH D)滤波算法在虚警、漏检情况下，b标状态估计不稳定和b标可观测性车弱的问题，提出了一种基于序贯融合的粒子PH D滤波方法，利用雷达和红外传感器多目标进行融合跟踪杏基本思想是先对红外传感器进行粒子PH D滤波，丙将红外传感器滤波结果作为雷达的预测值，然后利用P达观测的数据进行更新，这样通过雷达和红外传感器交替上作保证目标状态的可观测性，从滤波器输出结身即可得到目标的状态信息仿真结果表明，在虚警、漏检和密集目标环境下，该方法是有效的和稳健的(The problem of target state estimation instability and observability weakerin the presence offalse alarms and missed detection was deal with. On the basis of sequential fusion, a particleprobabil- ity hypothesis density(PHD) filter for multrsensor multrtarget tracking was proposed. Observed da to collected from the infrared sensor was estimated with the particle PHD filter. Then the results from the filter were set as the radar predicted value by the radar observations. The multrtarget state can be updated to guarantee observing the target state. In this way, the global state is updated at the fusion center. Simulation results show that the proposed algorithm is effective and robust under the false warning, omission and concentrated target environment. )

1990年—adaptive multi-band CFAR detection of an optical pattern with unknown spectral distribution.pdf

著名专家写的计算机视觉方面的原著，希望对大家有所帮助(Writing a well-known experts in the computer vision aspects of the original, and they hope to help everyone)