解释相机校准结果？

Question

我在一些棋盘图像（40~）上使用了 OpenCV 的 findChessboardCorners，大约 27 个似乎准确地找到了角落。如何从这里开始？我是否只计算正确识别的图像的重投影误差？这正常吗？

部分正确识别的图片-

部分图片识别错误-

我如何校准图像 -

import cv2 as cv
def calibrate():

    criteria = (cv.TERM_CRITERIA_EPS + cv.TERM_CRITERIA_MAX_ITER, 30, 0.001)

    objp = np.zeros((6*9,3),np.float32)
    objp[:,:2] = np.mgrid[0:9, 0:6].T.reshape(-1,2)

    objpoints = []
    imgpoints = []

    images = glob.glob('*.png')

    for fname in images:
        img = cv.imread(fname)
        gray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)

        ret, corners = cv.findChessboardCorners(gray, (9,6), None)

        if ret == True:
            print('Hello')

            objpoints.append(objp)

            corners2 = cv.cornerSubPix(gray, corners, (11,11), (-1,-1), criteria)
         #   cv.drawChessboardCorners(img, (9,6), corners, ret)
            imgpoints.append(corners2)

            cv.imshow('img',img)
            cv.waitKey(500)
    cv.destroyAllWindows()

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

    return objpoints, imgpoints, ret, mtx, dist, rvecs, tvecs

如果有人想试一试，我已经添加了原始图像。 https://imgur.com/a/rsl0SHr

Answer 1

Is this normal to expect?

不是，你错误识别的图像很奇怪。我认为您的校准过程可能有问题。你能展示一些代码吗（例如 findChessboardCorner() 和 calibrateCamera() 调用）？

Do I calculate the reprojection error over just the correctly identified images?

您应该计算所有点的重投影误差，但首先您需要修复校准过程。

解释相机校准结果？

Interpreting camera calibration results?

python

camera

opencv

camera-calibration