BM算法实现双目视觉测距--python实现

最新推荐文章于 2025-05-04 17:52:28 发布

白嫖怪阿七

最新推荐文章于 2025-05-04 17:52:28 发布

阅读量5.4k

点赞数 7

分类专栏：视觉 BM算法文章标签： python opencv

本文链接：https://blog.youkuaiyun.com/weixin_59410783/article/details/124352648

版权

在完成对双目摄像头的标定之后，获得标定的矩阵包括左右相机的内参数矩阵、畸变矩阵、旋转矩阵和平移矩阵。将其放入代码中，如下所示：

import cv2
import numpy as np

# 左相机内参
left_camera_matrix = np.array([(426.61499943, 0, 337.77666426),
                   (0, 426.50296492, 254.57967858),
                   (0, 0, 1)])


# 左相机畸变系数:[k1, k2, p1, p2, k3]
left_distortion = np.array([[1.64160258e-02 ,1.90313751e-02  ,3.85843636e-05 ,-6.81027605e-04,  -7.77682876e-02]])

# 右相机内参
right_camera_matrix = np.array([( 428.37039364, 0, 335.14944239),
                   (0, 428.26149388, 253.70369704),
                   (0, 0, 1)])

# 右相机畸变系数:[k1, k2, p1, p2, k3]
right_distortion = np.array([[1.18624707e-02 , 2.92395356e-02 , 7.84349618e-04 ,-4.59924352e-05,  -8.34482148e-02]])

# om = np.array([-0.00009, 0.02300, -0.00372])
# R = cv2.Rodrigues(om)[0]

# 旋转矩阵
R = np.array([(9.99999401e-01 ,-1.08818183e-03 , 1.21838861e-04),
                   (1.08825693e-03 , 9.99999217e-01, -6.18081935e-04),
                   (-1.21166180e-04 , 6.18214157e-04 , 9.99999802e-01)])

# 平移向量
T = np.array([[-59.98598553], [-0.81926245], [0.12784464]])
doffs = 0.0

size = (640, 480)

R1, R2, P1, P2, Q, validPixROI1, validPixROI2 = cv2.stereoRectify(left_camera_matrix, left_distortion,
                                                                  right_camera_matrix, right_distortion, size, R,
                                                                  T)

left_map1, left_