OpenCV 3 Computer Vision with Python Cookbook

How to do it

You need to complete the following steps:

1. Import the necessary modules:

import cv2import numpy as np

2. Load the left/right image point correspondences and the individual camera calibration parameters:

data = np.load('../data/stereo/case1/stereo.npy').item()Kl, Kr, Dl, Dr, left_pts, right_pts, E_from_stereo, F_from_stereo = \    data['Kl'], data['Kr'], data['Dl'], data['Dr'], \    data['left_pts'], data['right_pts'], data['E'], data['F']

3. Stack the left and right point lists into arrays:

left_pts = np.vstack(left_pts)right_pts = np.vstack(right_pts)

4. Get rid of lens distortions:

left_pts = cv2.undistortPoints(left_pts, Kl, Dl, P=Kl)right_pts = cv2.undistortPoints(right_pts, Kr, Dr, P=Kr)

5. Estimate the fundamental matrix:

F, mask ...