python/C++ 去畸变

 

鱼眼畸变

python

opencv文档

void cv::fisheye::undistortPoints(InputArray  distorted,
OutputArray     undistorted,
InputArray     K,
InputArray     D,
InputArray     R = noArray(),
InputArray     P = noArray() 
)        
Python:
undistorted    =    cv.fisheye.undistortPoints(    distorted, K, D[, undistorted[, R[, P]]]    )
#include <opencv2/calib3d.hpp>

Undistorts 2D points using fisheye model.

Parameters
distorted    Array of object points, 1xN/Nx1 2-channel (or vector<Point2f> ), where N is the number of points in the view.
K    Camera intrinsic matrix cameramatrixK.
D    Input vector of distortion coefficients (k1,k2,k3,k4).
R    Rectification transformation in the object space: 3x3 1-channel, or vector: 3x1/1x3 1-channel or 1x1 3-channel
P    New camera intrinsic matrix (3x3) or new projection matrix (3x4)
undistorted    Output array of image points, 1xN/Nx1 2-channel, or vector<Point2f> .

 

对于python中的 InputArray 

参考链接

输入点需要是一个形状为 的数组(n_points, 1, n_dimensions)。所以如果你有 2D 坐标，它们应该在 shape 中 (n_points, 1, 2) 。或者对于 3D 坐标，它们应该在 shape 中 (n_points, 1, 3) 。对于大多数OpenCV 函数来说都是如此。AFAIK，这种格式适用于所有OpenCV 函数，而一些 OpenCV 函数也将接受形状中的点(n_points, n_dimensions)。发现最好保持所有内容的一致性和格式(n_points, 1, n_dimensions)。

需要明确的是，这意味着四个 32 位浮点 2D 点的数组将如下所示：

points = np.array([[[x1, y1]], [[x2, y2]], [[x3, y3]], [[x4, y4]]], dtype=np.float32)

可以使用 np.newaxis 将 (n_points, n_dimensions) 转换成 (n_points, 1, n_dimensions) ：

>>> points = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
>>> points.shape
(4, 2)
>>> points = points[:, np.newaxis, :]
>>> points.shape
(4, 1, 2)