相机畸变校正、求出参数、具体应用

一、原理

前提:摄像头固定因为摄像头一动,内参不变(畸变系数),但是外参(坐标变换)会变。
通过拍摄几张标定板的照片,然后得到畸变系数和相机内外参系数,然后每次读取摄像机图片时,将这些系数带进去,计算之后就可以得到矫正后的图片了。
效果如下:

畸变校正前
相机畸变校正、求出参数、具体应用_第1张图片

畸变校正后
相机畸变校正、求出参数、具体应用_第2张图片

显然上面图片四周直线都是弯曲的,被矫正后,变得效果不错了。

二、具体步骤

标定图:相机畸变校正、求出参数、具体应用_第3张图片
程序在第三部分,具体步骤如下:
1、将第三步的代码复制到工程里
2、 在工程目录下(主函数.cpp相同目录下)建立一个caliberation文件夹,采集10——20张照片(不同角度,方向,但是要把角点全部显示出来),将照片放入该文件夹下。

效果如下:
相机畸变校正、求出参数、具体应用_第4张图片
3、新建一个calibdata.txt文件,将步骤2的图片路径写进去格式如下:

./caliberation/1.jpg
./caliberation/2.jpg
./caliberation/3.jpg
./caliberation/4.jpg
./caliberation/5.jpg
./caliberation/6.jpg
./caliberation/7.jpg
./caliberation/8.jpg
./caliberation/9.jpg
./caliberation/10.jpg
./caliberation/11.jpg
./caliberation/12.jpg

4、新建一个chess文件夹(名字随便,记得在程序里改),用于保存畸变校正后的图片。
5、运行程序,会生成一个caliberation_result.txt文件,里面保存了内外参等一些参数。比如畸变系数,旋转矩阵,平移矩阵等。

三、参数获取程序代码

//2018.6.19:畸变校正



#include "opencv2/core/core.hpp"    
#include "opencv2/imgproc/imgproc.hpp"    
#include "opencv2/calib3d/calib3d.hpp"    
#include "opencv2/highgui/highgui.hpp"    
#include     
#include     

using namespace cv;
using namespace std;



void main()
{
	ifstream fin("calibdata.txt"); /* 标定所用图像文件的路径 */
	ofstream fout("caliberation_result.txt");  /* 保存标定结果的文件 */
	//读取每一幅图像,从中提取出角点,然后对角点进行亚像素精确化     
	cout << "开始提取角点………………";
	int image_count = 0;  /* 图像数量 */
	Size image_size;  /* 图像的尺寸 */
	Size board_size = Size(4, 6);    /* 标定板上每行、列的角点数 */
	vector image_points_buf;  /* 缓存每幅图像上检测到的角点 */
	vector> image_points_seq; /* 保存检测到的所有角点 */
	string filename;
	int count = -1;//用于存储角点个数。    
	while (getline(fin, filename))
	{
		image_count++;
		// 用于观察检验输出    
		cout << "image_count = " << image_count << endl;
		/* 输出检验*/
		cout << "-->count = " << count;
		Mat imageInput = imread(filename);
		if (imageInput.empty())
		{
			cout << "can not open pic!\n";
			exit(-1);
		}
		if (image_count == 1)  //读入第一张图片时获取图像宽高信息    
		{
			image_size.width = imageInput.cols;
			image_size.height = imageInput.rows;
			cout << "image_size.width = " << image_size.width << endl;
			cout << "image_size.height = " << image_size.height << endl;
		}

		/* 提取角点 */
		if (0 == findChessboardCorners(imageInput, board_size, image_points_buf))
		{
			cout << "can not find chessboard corners!\n"; //找不到角点    
			exit(1);
		}
		else
		{
			Mat view_gray;
			cvtColor(imageInput, view_gray, CV_RGB2GRAY);
			/* 亚像素精确化 */
			find4QuadCornerSubpix(view_gray, image_points_buf, Size(5, 5)); //对粗提取的角点进行精确化    
			//cornerSubPix(view_gray,image_points_buf,Size(5,5),Size(-1,-1),TermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER,30,0.1));    
			image_points_seq.push_back(image_points_buf);  //保存亚像素角点    
			/* 在图像上显示角点位置 */
			drawChessboardCorners(view_gray, board_size, image_points_buf, false); //用于在图片中标记角点    
			namedWindow("Camera Calibration", 0);//创建窗口
			imshow("Camera Calibration", view_gray);//显示图片    
			waitKey(500);//暂停0.5S           
		}
	}
	int total = image_points_seq.size();
	cout << "total = " << total << endl;
	int CornerNum = board_size.width*board_size.height;  //每张图片上总的角点数    
	for (int ii = 0; ii 第 " << j << "图片的数据 --> : " << endl;
		}
		if (0 == ii % 3)  // 此判断语句,格式化输出,便于控制台查看    
		{
			cout << endl;
		}
		else
		{
			cout.width(10);
		}
		//输出所有的角点    
		cout << " -->" << image_points_seq[ii][0].x;
		cout << " -->" << image_points_seq[ii][0].y;
	}
	cout << "角点提取完成!\n";

	//以下是摄像机标定    
	cout << "开始标定………………";
	/*棋盘三维信息*/
	Size square_size = Size(10, 10);  /* 实际测量得到的标定板上每个棋盘格的大小 */
	vector> object_points; /* 保存标定板上角点的三维坐标 */
	/*内外参数*/
	Mat cameraMatrix = Mat(3, 3, CV_32FC1, Scalar::all(0)); /* 摄像机内参数矩阵 */
	vector point_counts;  // 每幅图像中角点的数量    
	Mat distCoeffs = Mat(1, 5, CV_32FC1, Scalar::all(0)); /* 摄像机的5个畸变系数:k1,k2,p1,p2,k3 */
	vector tvecsMat;  /* 每幅图像的旋转向量 */
	vector rvecsMat; /* 每幅图像的平移向量 */
	/* 初始化标定板上角点的三维坐标 */
	int i, j, t;
	for (t = 0; t tempPointSet;
		for (i = 0; i image_points2; /* 保存重新计算得到的投影点 */
	cout << "\t每幅图像的标定误差:\n";
	fout << "每幅图像的标定误差:\n";
	for (i = 0; i tempPointSet = object_points[i];
		/* 通过得到的摄像机内外参数,对空间的三维点进行重新投影计算,得到新的投影点 */
		projectPoints(tempPointSet, rvecsMat[i], tvecsMat[i], cameraMatrix, distCoeffs, image_points2);
		/* 计算新的投影点和旧的投影点之间的误差*/
		vector tempImagePoint = image_points_seq[i];
		Mat tempImagePointMat = Mat(1, tempImagePoint.size(), CV_32FC2);
		Mat image_points2Mat = Mat(1, image_points2.size(), CV_32FC2);
		for (int j = 0; j < tempImagePoint.size(); j++)
		{
			image_points2Mat.at(0, j) = Vec2f(image_points2[j].x, image_points2[j].y);
			tempImagePointMat.at(0, j) = Vec2f(tempImagePoint[j].x, tempImagePoint[j].y);
		}
		err = norm(image_points2Mat, tempImagePointMat, NORM_L2);
		total_err += err /= point_counts[i];
		std::cout << "第" << i + 1 << "幅图像的平均误差:" << err << "像素" << endl;
		fout << "第" << i + 1 << "幅图像的平均误差:" << err << "像素" << endl;
	}
	std::cout << "总体平均误差:" << total_err / image_count << "像素" << endl;
	fout << "总体平均误差:" << total_err / image_count << "像素" << endl << endl;
	std::cout << "评价完成!" << endl;
	//保存定标结果        
	std::cout << "开始保存定标结果………………" << endl;
	Mat rotation_matrix = Mat(3, 3, CV_32FC1, Scalar::all(0)); /* 保存每幅图像的旋转矩阵 */
	fout << "相机内参数矩阵:" << endl;
	fout << cameraMatrix << endl << endl;
	fout << "畸变系数:\n";
	fout << distCoeffs << endl << endl << endl;
	for (int i = 0; i> imageFileName;
		filePath += imageFileName;
		filePath += ".jpg";
		Mat imageSource = imread("1.jpg"); //读取畸变图片
		Mat newimage = imageSource.clone(); //校正后输出图片
		//另一种不需要转换矩阵的方式    
		//	undistort(imageSource,newimage,cameraMatrix,distCoeffs);    
		remap(imageSource, newimage, mapx, mapy, INTER_LINEAR);
		StrStm.clear();
		filePath.clear();
		StrStm << i + 1;
		StrStm >> imageFileName;
		imageFileName += "_d.jpg";
		imwrite(imageFileName, newimage);
	}
	std::cout << "保存结束" << endl;
	return;
}

四、使用程序

这个部分就是将得到的参数,应用到具体的程序中,不用每次进行标定,只要摄像头位置不变,就可以将畸变参数带进去就可以矫正。


void InitMat(Mat& m, float* num)
{
	for (int i = 0; i(i, j) = *(num + i * m.rows + j);
}




int main()
{
	int i = 1000;
	int n = 1;
	Mat edges;
	Mat frame = imread("2.jpg"); //读取畸变图片

	Mat R = Mat::eye(3, 3, CV_32F);

	Size image_size;  /* 图像的尺寸 */
	//获取图像大小
	image_size.width = 1920;
	image_size.height = 1080;

	//cameraMatrix为 "相机内参数矩阵:" << endl;
	Mat mapx = Mat(image_size, CV_32FC1);
	Mat mapy = Mat(image_size, CV_32FC1);

	//参数矩阵
	float neican_data[] = { 9558.649257742036, 0, 959.3165310990756, 0, 9435.752651759443, 532.7507141910969, 0, 0, 1 };
	Mat cameraMatrix(3, 3, CV_32FC1);
	InitMat(cameraMatrix, neican_data);

	cout << "cameraMatrix= " << endl << " " << cameraMatrix << endl << endl;
	//测得的畸变系数
	float jibian_data[] = { -6.956561513881647, -68.83902522804168, -0.004834538444671919, 0.01471273691928269, -0.4916103704308509 };
	Mat distCoeffs(1, 5, CV_32FC1); /* 摄像机的5个畸变系数:k1,k2,p1,p2,k3 */
	InitMat(distCoeffs, jibian_data);
	cout << "distCoeffs= " << endl << " " << distCoeffs << endl << endl;









	i = 0;
	namedWindow("【原始图】", 0);//参数为零,则可以自由拖动
	imshow("【原始图】", frame);
	/********相机矫正*******************************************************************************/

	initUndistortRectifyMap(cameraMatrix, distCoeffs, R, cameraMatrix, image_size, CV_32FC1, mapx, mapy);


	Mat imageSource = frame; //读取畸变图片
	Mat newimage = imageSource.clone(); //校正后输出图片

	remap(imageSource, newimage, mapx, mapy, INTER_LINEAR);

	namedWindow("畸变校正后的图片", 0);//参数为零,则可以自由拖动
	imshow("畸变校正后的图片", newimage);
	}

上面只是矫正部分的代码

你可能感兴趣的:(opencv,图像识别与处理)