Matlab 双目相机标定 opencv应用

只记录坑点注意点：

1.双目数据获得

原始数据获得----其实是一张图片，从中间一分为二，分别为左右相机画面

cap = cv2.VideoCapture(1)
cap.set(3,1280)
cap.set(4,480)

while True:
    ret1, frame = cap.read()

    # ret2, frame2 = camera2.read()
    # if not ret1 or not ret2:
    if ret1 != True:
        break
    #cv2.resize(frame, (2560, 360), interpolation=cv2.INTER_LINEAR)
    dsize = (1280, 480)
    imagedst = cv2.resize(frame, dsize, interpolation=cv2.INTER_LINEAR)

    frame1 = imagedst[0:480, 0:640]
    frame2 = imagedst[0:480, 640:1280]

2.标定数据使用

        MATLAB标定双目相机流程就不介绍了，网上一堆，只记录MATLAB标定完的数据如何使用到opencv进行立体匹配，下面图片是各种标定结果

 

 

填入opencv前的中间处理 

1.相机内参和旋转矩阵转置后填入

2.K1-3，P1-2按照顺序填入

3.平移矩阵直接填入

对应实际填入opencv的数据----转置后的

# 双目相机参数
class stereoCamera(object):
    def __init__(self):
        # 左相机内参
        self.cam_matrix_left = np.array([[496.8881739318051, 29.112084239370530, 342.2427649003997],
                                [0., 482.43229620875210, 241.1432000960281],
                                 [0., 0., 1.]])
        # 右相机内参
        self.cam_matrix_right = np.array([[500.0071875044045, 27.945379795056090, 330.7537796063574],
                                          [0., 482.1375852282574, 245.4564457477531],
                                          [0., 0., 1.]])

        # 左右相机畸变系数:[k1, k2, p1, p2, k3]
        self.distortion_l = np.array([[-0.009251249167910, 0.422804323842635, -0.005152418761053,
                                       0.003651300040505, -0.649768579382033]])
        self.distortion_r = np.array([[-0.071705287118270,1.007117302831552, -0.003344136852431,
                                       -0.005290333871640, -2.480977479998242]])

        # 旋转矩阵
        self.R = np.array([[0.999166147463142, -0.0005777861684523863,0.040824942459317],
             [0.0006482001597173343, 0.999998325193149, -0.001711562867902],
              [-0.040823885168073, 0.001736598411085, 0.999164848573919]])

        # 平移矩阵
        self.T = np.array([[-117.0596521731195], [-5.996326944677823], [-2.421637085624411]])