calcOpticalFlowFarneback

//函数原型

void calcOpticalFlowFarneback( InputArray prev, InputArray next, InputOutputArray flow,
                                            double pyr_scale, int levels, int winsize,
                                            int iterations, int poly_n, double poly_sigma,
                                            int flags );

/*@param prev first 8-bit single-channel input image.输入的影像必须是单通道，8位的灰度影像
@param next second input image of the same size and the same type as prev.
@param flow computed flow image that has the same size as prev and type CV_32FC2.输出的结果是32位，2通道的影像，可以使用Point2f 或者Vec2f进行转换 
@param pyr_scale parameter, specifying the image scale (\<1) to build pyramids for each image;金字塔缩放级别，这个参数必须设置为小于1的浮点数
pyr_scale=0.5 means a classical pyramid, where each next layer is twice smaller than the previous
one.
@param levels number of pyramid layers including the initial image; levels=1 means that no extra金字塔缩放的次数
layers are created and only the original images are used.
@param winsize averaging window size; larger values increase the algorithm robustness to image 在使用之前，需要进行平滑处理，这个尺寸就是平滑内核的大小，

一般使用的是高斯内核
noise and give more chances for fast motion detection, but yield more blurred motion field.
@param iterations number of iterations the algorithm does at each pyramid level 迭代的次数，迭代的次数越高，精度越好；一般情况2~3次迭代就能够获得良好的

结果，但是选择6次，在大多数影像中都能获得良好的效果
@param poly_n size of the pixel neighborhood used to find polynomial expansion in each pixel; 拟合多边形的窗口尺寸 一般情况下选择5~7之间
larger values mean that the image will be approximated with smoother surfaces, yielding more
robust algorithm and more blurred motion field, typically poly_n =5 or 7.
@param poly_sigma standard deviation of the Gaussian that is used to smooth derivatives used as a这个参数一般选择0.2*polyN 
basis for the polynomial expansion; for poly_n=5, you can set poly_sigma=1.1, for poly_n=7, a
good value would be poly_sigma=1.5.
@param flags operation flags that can be a combination of the following:
 -   **OPTFLOW_USE_INITIAL_FLOW** uses the input flow as an initial flow approximation.
 -   **OPTFLOW_FARNEBACK_GAUSSIAN** uses the Gaussian \f$\texttt{winsize}\times\texttt{winsize}\f$
     filter instead of a box filter of the same size for optical flow estimation; usually, this
     option gives z more accurate flow than with a box filter, at the cost of lower speed;
     normally, winsize for a Gaussian window should be set to a larger value to achieve the same
     level of robustness.*/

//一段具体的代码

#include <iostream>
#include <vector>
#include <opencv2/opencv.hpp>  //头文件
#include <opencv2/xfeatures2d.hpp>
using namespace cv;  //包含cv命名空间
using namespace std;
//string filename="C:\\Users\\Administrator\\Desktop\\标准测试图片"
int main()
{
	string filename1 = "C:\\Users\\Administrator\\Desktop\\标准测试图片\\left08.jpg";
	string filename2 = "C:\\Users\\Administrator\\Desktop\\标准测试图片\\left09.jpg";
	Mat img1 = imread(filename1, IMREAD_GRAYSCALE);
	Mat img2 = imread(filename2, IMREAD_GRAYSCALE);
	Mat result;//保存结果 CF_32FC2
	Mat Out = Mat::zeros(img1.size(), CV_8UC3);
	calcOpticalFlowFarneback(img1, img2, result, 0.5, 6, 7, 6, 5, 1.1,OPTFLOW_FARNEBACK_GAUSSIAN);
	for (int i = 0; i < img1.rows;i+=30)
	{
		for (int j = 0; j < img1.cols;j+=30)
		{
			Point2f pt = result.at<Point2f>(i, j);
			line(Out, Point2f(j, i), Point2f(j + pt.x, i + pt.y), Scalar(255, 0, 0), 1, CV_AA);
		}
	}
	imshow("Result", Out);
	imwrite("Result.jpg", Out);
	waitKey(0);
	return 0;
}