去畸变方法：直接矫正和间接矫正

去畸变方法

如图两个公式，直接矫正很好理解，在标定之后得到畸变参数，k,p后依次对原图像像素点代入公式，计算出其正确位置，赋值给新的图像，代码如下：

#include<opencv2/opencv.hpp>
#include<string>
#include <iostream>
using namespace std;
string image_file = "D:\\360MoveData\\Users\\feimaojingzhang\\Desktop\\视觉\\tx\\c1\\28.jpg";
int main(int argc,char **argv)
{
	double k1 = 0.024928684812037, k2 = 0.012033182014521, p1 = -2.680375058702241e-04, p2 = 3.382391560956786e-04;
	double fx = 2.262872782992156e+03, fy = 2.413405973071257e+03, cx = 1.151552978915428e+03, cy = 1.043331731728508e+03;
	cv::Mat image = cv::imread(image_file, 0);
	int rows = image.rows, cols = image.cols;
	cv::Mat image_undistort = cv::Mat(rows, cols, CV_8UC1);

	for (int v = 0; v < rows; v++)
	{
		for (int u = 0; u < cols; u++) {
			double x = (u - cx) / fx, y = (v - cy) / fy;
			double r = sqrt(x*x + y * y);
			double x_distorted = x * (1 + k1 * r*r + k2 * r*r*r*r) + 2 * p1*x*y + p2 * (r*r + 2 * x*x);
			double y_distorted = y * (1 + k1 * r*r + k2 * r*r*r*r) + 2 * p2*x*y + p1 * (r*r + 2 * y*y);
			double u_distorted = fx * x_distorted + cx;
			double v_distorted = fy * y_distorted + cy;

			if (u_distorted >= 0 && v_distorted >= 0 && u_distorted < cols && v_distorted < rows) {
				image_undistort.at<uchar>(v,u) = image.at<uchar>((double)v_distorted, (double
					)u_distorted);
			}
			else {
				image_undistort.at<uchar>(v, u) = 0;
			}
		}
	}
	cv::imshow("distorted", image);
	cv::imshow("undistorted", image_undistort);
	cv::imwrite("D:\\360MoveData\\Users\\feimaojingzhang\\Desktop\\视觉\\tx\\c1\\b28.jpg", image_undistort);
	cv::waitKey();
	return 0;



}

这种去畸变方法直接方便好理解，是通过原图像直接投影到去畸变图像，但由于精度问题，总会产生一定空点和条纹，不利于后续求解RT矩阵等一系列操作，而间接纠正法利用反投影，能够避免上述情况的出现。OpenCV中undistorted()函数就是反投影操作。

```cpp
cv::undistorted();