双目图像的畸变矫正代码

双目图像的畸变矫正主要是通过相机标定得到相机内参和畸变系数，然后利用这些参数对图像进行矫正。下面是一个基于OpenCV库的双目图像畸变矫正代码示例：

import numpy as np
import cv2

# 相机标定参数
K_left = np.array([[fx_left, 0, cx_left], [0, fy_left, cy_left], [0, 0, 1]])
K_right = np.array([[fx_right, 0, cx_right], [0, fy_right, cy_right], [0, 0, 1]])
D_left = np.array([k1_left, k2_left, p1_left, p2_left, k3_left])
D_right = np.array([k1_right, k2_right, p1_right, p2_right, k3_right])
R = np.array([[r11, r12, r13], [r21, r22, r23], [r31, r32, r33]])
T = np.array([[tx], [ty], [tz]])

# 读入双目图像
img_left = cv2.imread('left.png')
img_right = cv2.imread('right.png')

# 矫正双目图像
R1, R2, P1, P2, Q, validPixROI1, validPixROI2 = cv2.stereoRectify(K_left, D_left, K_right, D_right, img_left.shape[::-1], R, T, alpha=0)
map1_left, map2_left = cv2.initUndistortRectifyMap(K_left, D_left, R1, P1, img_left.shape[::-1], cv2.CV_32FC1)
map1_right, map2_right = cv2.initUndistortRectifyMap(K_right, D_right, R2, P2, img_right.shape[::-1], cv2.CV_32FC1)
img_left_rectified = cv2.remap(img_left, map1_left, map2_left, cv2.INTER_LINEAR)
img_right_rectified = cv2.remap(img_right, map1_right, map2_right, cv2.INTER_LINEAR)

# 保存矫正后的图像
cv2.imwrite('left_rectified.png', img_left_rectified)
cv2.imwrite('right_rectified.png', img_right_rectified)

需要注意的是，上述代码中的相机标定参数需要根据实际情况进行填写。同时，矫正双目图像的过程也需要计算出视差图，这里未涉及到。