Fisheye_calibration

粒子滤波器使用示例，用于跟踪效果好，用VC++实现(example of particle filter)

一幅大小为256×256的256级灰度图像（每像素8bit） 如果图像的各个像素之间是统计独立的，求该图像的信息熵 -离散无记忆信源 如果图像的各个像素之间不是统计独立的，求该图像的信息熵 -图像像素的概率分布模型(A 256 gray scale image (8bit per pixel) with a size of 256 x 256 If each pixel of the image is statistically independent, the information entropy of the image is calculated Discrete memoryless source If each pixel of the image is not statistically independent, the information entropy of the image is calculated Probability distribution model of image pixels)

图形图像处理中的平滑处理，可以实现部分的功能，但是还可以继续完善(Graphic image processing smoothing, can achieve some of the functions, but can also continue to improve)

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. )

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. )

图像去雾c++版源代码，实现效果还不错，可直接运行。(Fog to remove the c++ version of the source code, the effect is not bad, can be run directly.)

opencv是图像处理中常用到的工具箱，本资料为基于此工具箱的图像处理匹配算法SURF的实现代码。(opencv is commonly used in image processing to the toolbox, the toolbox based on this information for the image processing algorithm to match the achievement of SURF code.)

meanshift算法，及其在图像处理方面的应用(meanshift algorithm)

基于自动种子选择的区域生长法，克服了传统区域法的很多缺点(Region growing method based on automatic seed selection, to overcome the many shortcomings of the traditional regional law)

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