opencv給的官方代碼利用xml讀取文件，不如簡單的讀取txt文本的格式，便於編輯。這份代碼有三個要注意的地方。
1.txt文件要標好照片
2.Size board_size = Size(7, 8);我用的是7*8（內角點）的標定板
3.Size square_size = Size(10, 10);一般情況下應該是這個10*10。
#include <opencv2/opencv.hpp>
#include <iostream>
#include <fstream>
using namespace cv;
using namespace std;
int main()
{
ifstream fin("t.txt"); /* 標定所用圖像文件的路徑 */
ofstream fout("caliberation_result.txt"); /* 保存標定結果的文件 */
//讀取每一幅圖像，從中提取出角點，然後對角點進行亞像素精確化
int image_count = 0; /* 圖像數量 */
Size image_size; /* 圖像的尺寸 */
Size board_size = Size(7, 8); /* 標定板上每行、列的角點數 */
vector<Point2f> image_points_buf; /* 緩存每幅圖像上檢測到的角點 */
vector<vector<Point2f>> image_points_seq; /* 保存檢測到的所有角點 */
string filename;
int count = -1;//用於存儲角點個數。
std::cout << "開始提取角點………………" << endl;
Mat imageInput[6];
while (getline(fin, filename))
{
/* 輸出檢驗*/
int i=image_count++;
// 用於觀察檢驗輸出
imageInput[i] = imread(filename);
if (image_count == 1) //讀入第一張圖片時獲取圖像寬高信息
{
image_size = imageInput[i].size();
std::cout << "the size of images are : "<<image_size << endl;
}
std::cout << "current image_count : " << image_count << endl;
/* 提取角點 */
if (0 == findChessboardCorners(imageInput[i], board_size, image_points_buf))
{
std::cout << "can not find chessboard corners!\n"; //找不到角點
exit(1);
}
else
{
Mat view_gray;
cvtColor(imageInput[i], view_gray, CV_RGB2GRAY);
/* 亞像素精確化 */
find4QuadCornerSubpix(view_gray, image_points_buf, Size(7, 7)); //對粗提取的角點進行精確化
image_points_seq.push_back(image_points_buf); //保存亞像素角點
/* 在圖像上顯示角點位置 */
drawChessboardCorners(view_gray, board_size, image_points_buf, true); //用於在圖片中標記角點
imshow("Camera Calibration", view_gray);//顯示圖片
waitKey(100);//暫停0.1S
}
}
int total = image_points_seq.size();
std::cout << "total = " << total << endl;
int CornerNum = board_size.width*board_size.height; //每張圖片上總的角點數
for (int i = 0; i<total; i++)
{
// 便於控制檯查看
std::cout << std::endl;
int j = i + 1;
std::cout << "----> 第 " << j << "張圖片的角點座標 : " << endl;;
//輸出所有的角點
for (int j = 0; j < CornerNum; j++)
{
std::cout << " ( " << image_points_seq[i][j].x;
std::cout << " ," << image_points_seq[i][j].y <<" )"<< endl;
}
}
std::cout << "角點提取完成！\n";
//以下是攝像機標定
std::cout << "開始標定………………" << endl;
/*棋盤三維信息*/
Size square_size = Size(10, 10); /* 實際測量得到的標定板上每個棋盤格的大小 */
vector<vector<Point3f>> object_points; /* 保存標定板上角點的三維座標 */
/*內外參數*/
Mat cameraMatrix = Mat(3, 3, CV_32FC1, Scalar::all(0)); /* 攝像機內參數矩陣 */
vector<int> point_counts; // 每幅圖像中角點的數量
Mat distCoeffs = Mat(1, 5, CV_32FC1, Scalar::all(0)); /* 攝像機的5個畸變係數：k1,k2,p1,p2,k3 */
vector<Mat> tvecsMat; /* 每幅圖像的旋轉向量 */
vector<Mat> rvecsMat; /* 每幅圖像的平移向量 */
/* 初始化標定板上角點的三維座標 */
int i, j, t;
for (t = 0; t<image_count; t++)
{
vector<Point3f> tempPointSet;
for (i = 0; i<board_size.height; i++)
{
for (j = 0; j<board_size.width; j++)
{
Point3f realPoint;
/* 假設標定板放在世界座標系中z=0的平面上 */
realPoint.x = i*square_size.width;
realPoint.y = j*square_size.height;
realPoint.z = 0;
tempPointSet.push_back(realPoint);
}
}
object_points.push_back(tempPointSet);
}
/* 初始化每幅圖像中的角點數量，假定每幅圖像中都可以看到完整的標定板 */
for (i = 0; i<image_count; i++)
{
point_counts.push_back(board_size.width*board_size.height);
}
/* 開始標定 */
calibrateCamera(object_points, image_points_seq, image_size, cameraMatrix, distCoeffs, rvecsMat, tvecsMat, 0);
std::cout << "標定完成！\n";
//對標定結果進行評價
std::cout << "開始評價標定結果………………\n";
double total_err = 0.0; /* 所有圖像的平均誤差的總和 */
double err = 0.0; /* 每幅圖像的平均誤差 */
vector<Point2f> image_points2; /* 保存重新計算得到的投影點 */
std::cout << "\t每幅圖像的標定誤差：\n\n";
fout << "每幅圖像的標定誤差：\n";
for (i = 0; i<image_count; i++)
{
vector<Point3f> tempPointSet = object_points[i];
/* 通過得到的攝像機內外參數，對空間的三維點進行重新投影計算，得到新的投影點 */
projectPoints(tempPointSet, rvecsMat[i], tvecsMat[i], cameraMatrix, distCoeffs, image_points2);
/* 計算新的投影點和舊的投影點之間的誤差*/
vector<Point2f> 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<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 << "幅圖像的平均誤差：" << err << "像素" << endl << endl;
fout << "第" << i + 1 << "幅圖像的平均誤差：" << err << "像素" << endl << endl;
}
std::cout << "總體平均誤差：" << total_err / image_count << "像素" << endl << endl;
fout << "總體平均誤差：" << total_err / image_count << "像素" << endl << endl;
std::cout << "評價完成！" << endl;
//保存定標結果
std::cout << "開始保存定標結果………………" << endl;
Mat rotation_matrix = Mat(3, 3, CV_32FC1, Scalar::all(0)); /* 保存每幅圖像的旋轉矩陣 */
fout << "相機內參數矩陣：" << endl;
fout << cameraMatrix << endl << endl;
fout << "畸變係數：\n";
fout << distCoeffs << endl << endl << endl;
for (int i = 0; i<image_count; i++)
{
fout << "第" << i + 1 << "幅圖像的旋轉向量：" << endl;
fout << tvecsMat[i] << endl;
/* 將旋轉向量轉換爲相對應的旋轉矩陣 */
Rodrigues(tvecsMat[i], rotation_matrix);
fout << "第" << i + 1 << "幅圖像的旋轉矩陣：" << endl;
fout << rotation_matrix << endl;
fout << "第" << i + 1 << "幅圖像的平移向量：" << endl;
fout << rvecsMat[i] << endl << endl;
}
std::cout << "完成保存" << endl;
fout << endl;
Mat dst;
undistort(imageInput[0], dst, cameraMatrix, distCoeffs);
imshow("result_ex",dst);
waitKey(500);
Mat map1, map2;
initUndistortRectifyMap(
cameraMatrix, distCoeffs, Mat(),
getOptimalNewCameraMatrix(cameraMatrix, distCoeffs, image_size, 1, image_size, 0), image_size,
CV_16SC2, map1, map2);
remap(imageInput[0], imageInput[0], map1, map2, INTER_LINEAR);
imshow("result_ex2", imageInput[0]);
waitKey(500);
return 0;
}