https://blog.csdn.net/u010128736/article/details/52875137

https://blog.csdn.net/h532600610/article/details/51800488

python 角点检测+相机标定+去畸变+重投影误差计算：

#coding:utf-8

importcv2importnumpy as npimportglob#找棋盘格角点#阈值

criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.001)#棋盘格模板规格

w = 9h= 6

#世界坐标系中的棋盘格点,例如(0,0,0), (1,0,0), (2,0,0) ....,(8,5,0)，去掉Z坐标，记为二维矩阵

objp = np.zeros((w*h,3), np.float32)

objp[:,:2] = np.mgrid[0:w,0:h].T.reshape(-1,2)#储存棋盘格角点的世界坐标和图像坐标对

objpoints = [] #在世界坐标系中的三维点

imgpoints = [] #在图像平面的二维点

images= glob.glob('calib/*.png')for fname inimages:

img=cv2.imread(fname)

gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)#找到棋盘格角点

ret, corners =cv2.findChessboardCorners(gray, (w,h),None)#如果找到足够点对，将其存储起来

if ret ==True:

cv2.cornerSubPix(gray,corners,(11,11),(-1,-1),criteria)

objpoints.append(objp)

imgpoints.append(corners)#将角点在图像上显示

cv2.drawChessboardCorners(img, (w,h), corners, ret)

cv2.imshow('findCorners',img)

cv2.waitKey(1)

cv2.destroyAllWindows()#标定

ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpoints, imgpoints, gray.shape[::-1], None, None)#去畸变

img2 = cv2.imread('calib/00169.png')

h, w= img2.shape[:2]

newcameramtx, roi=cv2.getOptimalNewCameraMatrix(mtx,dist,(w,h),0,(w,h)) #自由比例参数

dst =cv2.undistort(img2, mtx, dist, None, newcameramtx)#根据前面ROI区域裁剪图片#x,y,w,h = roi#dst = dst[y:y+h, x:x+w]

cv2.imwrite('calibresult.png',dst)#反投影误差

total_error =0for i inxrange(len(objpoints)):

imgpoints2, _=cv2.projectPoints(objpoints[i], rvecs[i], tvecs[i], mtx, dist)

error= cv2.norm(imgpoints[i],imgpoints2, cv2.NORM_L2)/len(imgpoints2)

total_error+=errorprint "total error:", total_error/len(objpoints)

标定 cv2.calibrateCamera函数文档：https://docs.opencv.org/2.4.1/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.html

c++ 角点检测+角点绘制：

#include #include#include#include

using namespacestd;intmain( )

{

cout<

IplImage* imgRGB =cvLoadImage(filename);

IplImage* imgGrey =cvLoadImage(filename,CV_LOAD_IMAGE_GRAYSCALE);if (imgGrey==NULL){//image validation

cout<< "No valid image input."<

}//-------find chessboard corners--------------

int corner_row=7;//interior number of row corners.(this can be countered by fingers.)

int corner_col=7;//interior number of column corners.

int corner_n=corner_row*corner_col;

CvSize pattern_size=cvSize(corner_row,corner_col);//CvPoint2D32f* corners=new CvPoint2D32f[corner_n];

CvPoint2D32f corners[49];intcorner_count;int found=cvFindChessboardCorners(//returning non-zero means sucess.

imgGrey,//8-bit single channel greyscale image.

pattern_size,//how many INTERIOR corners in each row and column of the chessboard.

corners,//an array where the corner locations can be recorded.

&corner_count,//optional, if non-NULL, its a point to an integer where the nuber of corners found can be recorded.//CV_CALIB_CB_ADAPTIVE_THRESH|CV_CALIB_CB_FILTER_QUADS//check page 382-383.

0);

cout<

cvDrawChessboardCorners(

imgRGB,

pattern_size,

corners,

corner_count,

found

);

cvSaveImage(filename2,imgRGB);//to summary a bit of findings.

cout<

cout<

cout<

cvNamedWindow("Find and Draw ChessBoard", 0);

cvShowImage("Find and Draw ChessBoard", imgRGB );

cvWaitKey(0);

cvReleaseImage(&imgGrey);

cvReleaseImage(&imgRGB);

cvDestroyWindow("Find and Draw ChessBoard");return 0;

}

注意事项：

pattern_size参数传递内点数，8*8的棋盘只有7*7内点。

图像选取应注意减少干扰，例如光照与背景等。

Corners中的角点坐标顺序排列规律不一定是以行从左上到右下。使用坐标计算映射关系时应提高警惕，对坐标进行重新排列。

关键函数参数说明：

int cvFindChessboardCorners( const void* image, CvSize pattern_size, CvPoint2D32f* corners, int* corner_count=NULL, int flags=CV_CALIB_CB_ADAPTIVE_THRESH );

Image:

输入的棋盘图，必须是8位的灰度或者彩色图像。

pattern_size:

棋盘图中每行和每列角点的个数。

Corners:

检测到的角点

corner_count:

输出，角点的个数。如果不是NULL，函数将检测到的角点的个数存储于此变量。

Flags:

各种操作标志，可以是0或者下面值的组合：

CV_CALIB_CB_ADAPTIVE_THRESH -使用自适应阈值(通过平均图像亮度计算得到)将图像转换为黑白图，而不是一个固定的阈值。

CV_CALIB_CB_NORMALIZE_IMAGE -在利用固定阈值或者自适应的阈值进行二值化之前，先使用cvNormalizeHist来均衡化图像亮度。

CV_CALIB_CB_FILTER_QUADS -使用其他的准则(如轮廓面积，周长，方形形状)来去除在轮廓检测阶段检测到的错误方块。