单目相机标定（使用OpenCV）

• 关于相机标定的理论知识和使用Matlab软件进行相机标定请看这篇博文：单目相机标定（使用Matlab）
• 这次因为项目原因需要给海康工业相机进行标定了，下载Matlab软件有些麻烦（主要是我电脑内存小。。。）

1.生成棋盘格

#include 
#include 
#include  

using namespace std;
using namespace cv;

int main()
{
	//单位转换
	int dot_per_inch = 96;  //根据自己的电脑设置，DPI：每英寸的像素点数
	double cm_to_inch = 0.3937; //1cm=0.3937inch
	double inch_to_cm = 2.54;   //1inch = 2.54cm
	double inch_per_dot = 1.0 / 96.0;

	//自定义标定板
	double blockSize_cm = 1.5; //方格尺寸：边长1.5cm的正方形
	//设置横列方框数目
	int blockcol = 10;
	int blockrow = 8;


	int blockSize = (int)(blockSize_cm / inch_to_cm * dot_per_inch);
	cout << blockSize << endl;

	//int imageSize = blockSize * blockNum;

	int imagesizecol = blockSize * blockrow;
	int imagesizerow = blockSize * blockcol;

	Mat chessBoard(imagesizecol, imagesizerow, CV_8UC3, Scalar::all(0));
	unsigned char color = 0;

	for (int i = 0; i < imagesizerow; i = i + blockSize) {
		color = ~color;
		for (int j = 0; j < imagesizecol; j = j + blockSize) {
			Mat ROI = chessBoard(Rect(i, j, blockSize, blockSize));
			ROI.setTo(Scalar::all(color));
			color = ~color;
		}
	}
	imshow("Chess board", chessBoard);
	imwrite("chessBoard.jpg", chessBoard);

	waitKey(0);

	return 0;
}

运行上述程序后会生成一个大小是10×8的，角点数是9×7的标定板，将其打印，为后续做标定准备。

2.相机标定过程

2.1 准备标定图片

• ①准备标定图片（不同位置、角度、姿态下拍摄，以10~20张为宜）。
  

2.2 VS的环境配置

• ②新建一个VS工程，配置好OpenCV的环境（这里我是VS2019+OpenCV4.4）
  PS：关于OpenCV的环境配置参考博文https://blog.csdn.net/qq_45445740/article/details/109582260中的3.1环境配置，关于在VS中配置Opencv。
• ③设置好图片的路径，新建一个image文件夹，里面放标定的图片，新建一个calibdata.txt文件，用于表示标定图片的路径。
  
  

2.3 源代码

PS：关于标定板的大小，依据自己拍摄的实际大小为准。
（本文中选用的标定板大小是10×8的，角点数是9×7的。）

Size board_size = Size(9, 7);    /* 标定板上每行、列的角点数 */

#include   
#include   
#include   
#include "opencv2/opencv.hpp"
#include 
using namespace cv;
using namespace std;


void LoadImages_TXT(string filename, vector<string>& imageNames)
{
	// step 1 : open file
	ifstream file(filename);

	if (!file)
	{
		cout << "Wrong! File " << filename << " dose not exist!" << endl;
		return;
	}

	// step 2 : load data
	imageNames.clear();

	while (!file.eof())
	{
		string imageName;
		file >> imageName;

		if (file.eof())
			break;
		imageNames.push_back(imageName);
		cout << "Load Image, imageName: " << imageName << endl;
	}
	file.close();
	return;
}

int main()
{
	std::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
	std::cout << "开始提取角点………………\n";
	int image_count = 0;  /* 图像数量 */
	Size image_size;  /* 图像的尺寸 */
	Size board_size = Size(9, 7);    /* 标定板上每行、列的角点数 */
	vector<Point2f> image_points_buf;  /* 缓存每幅图像上检测到的角点 */
	vector<vector<Point2f>> 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。

	string dataFileName = "calibdata.txt"; /* 标定所用图像文件的路径 */
	vector<string> imageNames;
	LoadImages_TXT(dataFileName, imageNames);

	for (int i = 0; i < imageNames.size(); i++)
	{
		image_count++;
		// 用于观察检验输出
		cout << "image_count = " << image_count << endl;
		/* 输出检验*/
		cout << "-->count = " << count << endl;

		string imageName = imageNames[i];
		Mat imageInput = imread(imageName);

		imshow("Camera Calibration", imageInput);//显示图片
		waitKey(100);//暂停0.1S

		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(找不到角点)!\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

			image_points_seq.push_back(image_points_buf);  //尾插,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,true); //用于在图片中标记角点
			drawChessboardCorners(imageInput, board_size, image_points_buf, true); //用于在图片中标记角点
			imshow("Camera Calibration", imageInput);//显示图片
			imwrite("Calibration" + to_string(image_count) + ".png", imageInput);//显示图片
			waitKey(100);//暂停0.1S
		}
	}


	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 < total; ii++)
	{
		if (0 == ii % CornerNum)// 24 是每幅图片的角点个数。此判断语句是为了输出 图片号，便于控制台观看
		{
			int i = -1;
			i = ii / CornerNum;
			int j = i + 1;
			cout << "--> 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(3个图片信息显示一行)
		{
			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";

	//
	// step 2 : 2D calibration
	//

	//以下是摄像机标定
	cout << "开始标定………………" << endl;
	/*棋盘三维信息*/
	Size square_size = Size(5, 5);  /* 实际测量得到的标定板上每个棋盘格的大小 */
	cout << "!!!!!!!!!!!!!!!!!!!!!!!1" << endl;
	cout << square_size.height << endl;
	cout << square_size.width << endl;
	vector<vector<Point3f>> object_points; /* 保存不同图片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<int> 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<Mat> tvecsMat;  /* 每幅图像的平移向量 */
	vector<Mat> rvecsMat; /* 每幅图像的旋转向量 */
	/* 初始化标定板上角点的三维坐标 */
	int i, j, t;
	for (t = 0; t < image_count; t++)  //图片个数
	{
		vector<Point3f> tempPointSet;
		for (i = 0; i < board_size.height; i++)
		{
			for (j = 0; j < board_size.width; j++)
			{
				Point3f realPoint;
				/* 假设标定板放在世界坐标系中z=0的平面上 */
				realPoint.x = i * square_size.height;
				realPoint.y = j * square_size.width;
				realPoint.z = 0;
				tempPointSet.push_back(realPoint);
			}
		}
		object_points.push_back(tempPointSet);
	}
	/* 初始化每幅图像中的角点数量，假定每幅图像中都可以看到完整的标定板 */
	for (i = 0; i < image_count; i++)
	{
		point_counts.push_back(board_size.width * board_size.height);
	}
	/* 开始标定 */
	calibrateCamera(object_points, image_points_seq, image_size, cameraMatrix, distCoeffs, rvecsMat, tvecsMat, 0);
	//cout<
	cout << "标定完成！\n";
	//对标定结果进行评价
	cout << "开始评价标定结果………………\n";
	double total_err = 0.0; /* 所有图像的平均误差的总和 */
	double err = 0.0; /* 每幅图像的平均误差 */
	vector<Point2f> 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 < image_count; i++)
	{
		vector<Point3f> 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，得到新的二维投影点 */
		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<Point2f> tempImagePoint = image_points_seq[i]; //原先的旧二维点
		Mat tempImagePointMat = Mat(1, tempImagePoint.size(), CV_32FC2);
		Mat image_points2Mat = Mat(1, image_points2.size(), CV_32FC2);  //32位浮点型2通道
		for (int j = 0; j < tempImagePoint.size(); j++)   //j对应二维点的个数
		{
			image_points2Mat.at<Vec2f>(0, j) = Vec2f(image_points2[j].x, image_points2[j].y);
			tempImagePointMat.at<Vec2f>(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;
	for (int i = 0; i < image_count; i++)
	{
		fout << "第" << i + 1 << "幅图像的旋转向量：" << endl;
		fout << rvecsMat[i] << endl;
		/* 将旋转向量转换为相对应的旋转矩阵 */
		Rodrigues(rvecsMat[i], rotation_matrix);
		fout << "第" << i + 1 << "幅图像的旋转矩阵：" << endl;
		fout << rotation_matrix << endl;
		fout << "第" << i + 1 << "幅图像的平移向量：" << endl;
		fout << tvecsMat[i] << endl << endl;
	}
	std::cout << "完成保存" << endl;
	fout << endl;
}

2.4 输出效果

我这里用了二十几张标定图片，运行时间长一点，静静等待…


之后会在工程目录中生成caliberation_result.txt标定结果和相关图片。