OPENCV相机标定+去畸变
将相机标定测量内参矩阵、畸变系数与去畸变返回无畸变图融合
使用时修改dir为存放图片的文件夹名称
修改board_size为行列的角点数
建议目录下存放多几张图片进行去畸变
下一步与去透视变换融合，生成一个矩阵，同时完成去畸变与透视变换。
#include
#include
#include
#include
#include
#include
#include
using namespace cv;
using namespace std;
#define linux 1
vector getFilesList(string dir);
#ifdef linux
#include
#include
vector getFilesList(string dirpath) {
vector allPath;
DIR *dir = opendir(dirpath.c_str());
if (dir == NULL)
{
cout << "opendir error" << endl;
return allPath;
}
struct dirent *entry;
while ((entry = readdir(dir)) != NULL)
{
if (entry->d_type == DT_DIR) {//It's dir
if (strcmp(entry->d_name, ".") == 0 || strcmp(entry->d_name, "..") == 0)
continue;
string dirNew = dirpath + "/" + entry->d_name;
vector tempPath = getFilesList(dirNew);
allPath.insert(allPath.end(), tempPath.begin(), tempPath.end());
}
else {
//cout << "name = " << entry->d_name << ", len = " << entry->d_reclen << ", entry->d_type = " << (int)entry->d_type << endl;
string name = entry->d_name;
string imgdir = dirpath + "/" + name;
//sprintf("%s",imgdir.c_str());
allPath.push_back(imgdir);
}
}
closedir(dir);
//system("pause");
return allPath;
}
#endif
#ifdef _WIN32//__WINDOWS_
#include
vector getFilesList(string dir)
{
vector allPath;
// 在目录后面加上"\\*.*"进行第一次搜索
string dir2 = dir + "\\*.*";
intptr_t handle;
_finddata_t findData;
handle = _findfirst(dir2.c_str(), &findData);
if (handle == -1) {// 检查是否成功
cout << "can not found the file ... " << endl;
return allPath;
}
while (_findnext(handle, &findData) == 0)
{
if (findData.attrib & _A_SUBDIR) 是否含有子目录
{
//若该子目录为"."或".."，则进行下一次循环，否则输出子目录名，并进入下一次搜索
if (strcmp(findData.name, ".") == 0 || strcmp(findData.name, "..") == 0)
continue;
// 在目录后面加上"\\"和搜索到的目录名进行下一次搜索
string dirNew = dir + "\\" + findData.name;
vector tempPath = getFilesList(dirNew);
allPath.insert(allPath.end(), tempPath.begin(), tempPath.end());
}
else //不是子目录，即是文件，则输出文件名和文件的大小
{
string filePath = dir + "\\" + findData.name;
allPath.push_back(filePath);
}
}
_findclose(handle); // 关闭搜索句柄
return allPath;
}
#endif
cv::Mat NewCameraMatrix;
int main() {
string dir = "../img6";
//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(6, 8); //6 4 10 7 9 6 69 68 68/* 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;
vector allFileList = getFilesList(dir);
int pic_num = allFileList.size();
string pic_name[pic_num];
for (size_t i = 0; i < allFileList.size(); i++)
pic_name[i] = allFileList.at(i);
while (image_count < pic_num) {
filename = pic_name[image_count];
image_count++;
// 用于观察检验输出
cout << "image_count = " << image_count << endl;
/* 输出检验*/
Mat imageInput = imread(filename);
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, COLOR_RGB2GRAY);
/* 亚像素精确化 */
find4QuadCornerSubpix(view_gray, image_points_buf, Size(11, 11)); //对粗提取的角点进行精确化
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, true); //用于在图片中标记角点
// imshow("Camera Calibration", view_gray);//显示图片
// waitKey(50);//暂停0.5S
}
}
int total = image_points_seq.size();
cout << "total = " << total << endl;
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 < image_count; t++) {
vector 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.width;
realPoint.y = j * square_size.height;
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 << "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 image_points2; /* 保存重新计算得到的投影点 */
for (i = 0; i < image_count; i++) {
vector 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 << "总体平均误差：" << total_err / image_count << "像素" << endl;
std::cout << "评价完成！" << endl;
Mat rotation_matrix = Mat(3, 3, CV_32FC1, Scalar::all(0)); /* 保存每幅图像的旋转矩阵 */
cout << "相机内参数矩阵：" << endl;
cout << cameraMatrix << endl << endl;
cout << "畸变系数：\n";
cout << distCoeffs << endl << endl << endl;
Mat K = cameraMatrix;
Mat D = distCoeffs;
//D.at(0,4)=0;
const int nImage = pic_num;
int ImgWidth = image_size.width;
int ImgHeight = image_size.height;
/***************************************************/
double fx = K.at(0, 0)
, fy = K.at(1, 1)
, ux = K.at(0, 2)
, uy = K.at(1, 2);
double k1 = D.at(0, 0), k2 = D.at(0, 1), k3 = D.at(0, 4), p1 = D.at(0,
2), p2 = D.at(
0, 3);
double k4 = 0, k5 = 0, k6 = 0;
/**********************way2***********************/
// Mat out2 = Mat(ImgHeight, ImgWidth, CV_8UC1);
for (int i = 0; i < nImage; i++) {
string InputPath = pic_name[i];
cv::Mat img_tmp = cv::imread(InputPath);
cvtColor(img_tmp, img_tmp, COLOR_RGB2GRAY);
// ///**********way2**********/
int max_x=-9999999,max_y=-9999999,min_x=9999999,min_y=9999999;
double point_xy[4][2];//左上 右上，左下，右下
for (int i = 0; i < ImgHeight; i++) {
for (int j = 0; j < ImgWidth; j++) {
double xDistortion = (j - ux) / fx;
double yDistortion = (i - uy) / fy;
double xCorrected, yCorrected;
double x0 = xDistortion;
double y0 = yDistortion;
for (int j = 0; j < 10; j++) {
double r2 = xDistortion * xDistortion + yDistortion * yDistortion;
double distRadialA = 1 / (1. + k1 * r2 + k2 * r2 * r2 + k3 * r2 * r2 * r2);
double distRadialB = 1. + k4 * r2 + k5 * r2 * r2 + k6 * r2 * r2 * r2;
double deltaX = 2. * p1 * xDistortion * yDistortion + p2 * (r2 + 2. * xDistortion * xDistortion);
double deltaY = p1 * (r2 + 2. * yDistortion * yDistortion) + 2. * p2 * xDistortion * yDistortion;
xCorrected = (x0 - deltaX) * distRadialA * distRadialB;
yCorrected = (y0 - deltaY) * distRadialA * distRadialB;
xDistortion = xCorrected;
yDistortion = yCorrected;
}
float kk=1.5;
xCorrected = xCorrected * fx + ux;
yCorrected = yCorrected * fy + uy;
if(yCorrected>max_y&&abs(yCorrected)max_x&&abs(xCorrected)ImgWidth*kk||abs(yCorrected)>ImgHeight)
{
img_tmp.at(i,j)=127;
}
}
}
cout<<"size: "<(i, j) = 0;
for (int i = -move_y; i < ImgHeight_out; i++) {
for (int j = -move_x; j < ImgWidth_out; j++) {
double xCorrected = (j - ux) / fx;
double yCorrected = (i - uy) / fy;
double xDistortion, yDistortion;
//我们已知的是经过畸变矫正或理想点的坐标；
double r2 = xCorrected * xCorrected + yCorrected * yCorrected;
double deltaRa = 1. + k1 * r2 + k2 * r2 * r2 + k3 * r2 * r2 * r2;
double deltaRb = 1 / (1. + k4 * r2 + k5 * r2 * r2 + k6 * r2 * r2 * r2);
double deltaTx = 2. * p1 * xCorrected * yCorrected + p2 * (r2 + 2. * xCorrected * xCorrected);
double deltaTy = p1 * (r2 + 2. * yCorrected * yCorrected) + 2. * p2 * xCorrected * yCorrected;
//下面为畸变模型；
xDistortion = xCorrected * deltaRa * deltaRb + deltaTx;
yDistortion = yCorrected * deltaRa * deltaRb + deltaTy;
//最后再次通过相机模型将归一化的坐标转换到像素坐标系下；
xDistortion = xDistortion * fx + ux;
yDistortion = yDistortion * fy + uy;
if (yDistortion >= 0 && yDistortion < ImgHeight && xDistortion >= 0 && xDistortion < ImgWidth)
out1.at(i+move_y, j+move_x) = img_tmp.at(yDistortion, xDistortion);
}
}
cv::imshow("ou1", out1);
cv::imshow("RawImage", img_tmp);
cv::waitKey(0);
}
}