Fisheye_calibration

图像亮度和对比度调节，已验证，分别有亮度调节和对比度调节的调整框(Image brightness and contrast adjustment, has been verified, respectively, brightness adjustment and contrast ad)

实现人体跟踪的源代码，实现对视频中目标人物的跟踪(The human tracking source code, the video of the target person tracking)

各种图像处理技术举例。其中原代码可以直接使用，非常不错。(various image processing technology, for example. The original code which can be used directly, very good.)

亚像素级cvFindCornerSubPix角点检测，可较为精确地对角点进行检测(The subpixel cvFindCornerSubPix corner detection)

光斑中心提取算法，在VS2010下，用opencv2.3.1编写的控制台程序，主要功能是利用hession矩阵和高斯滤波进行光斑中心点提取，里面附测试图片，提取精度为亚像素级别。(Spot center extraction algorithm, in VS2010, written by opencv2.3.1 console program, the main function is to use hession matrices and Gaussian filter for extracting the center spot, which is attached test images, the extraction accuracy of sub-pixel level.)

改程序就代码可以找出从不同角度或区间的两幅遥感影像的同名点(Change the program code can find it from different angles of the same name point or interval of two remote sensing images)

非常好的程序，能够对视频中移动目标进行跟踪(failed to translate)

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. )

运用openCV编写的C++图像色彩转移程序，原理是先转化到Lab图像，再保持L不变调整图像的a、b分量的均值跟方差。(Using openCV prepared C++ image color transfer process, the principle is first converted to Lab image, and then adjust the image to keep L constant a, b, with the mean variance component.)

一种快速图像阈值分割法，不是otsu或迭代法，Wellner 1993快速自适应的图像二值化方法，有具体使用方法，很详细(A fast image thresholding segmentation method, not otsu or iterative methods, Wellner 1993 fast adaptive image binarization method)