Aligning two views through stereo rectification

In this recipe, you will learn how to rectify two images captured using a stereo camera with known parameters in such a way that, for the point (x_l, y_l) in the left image, the corresponding epipolar line in the right image is y_r=y_l and vice versa. This greatly simplifies feature matching and dense stereo estimation algorithms.

Getting ready

Before you proceed with this recipe, you need to install the OpenCV version 3.3 (or greater) Python API package.

How to do it

You need to complete the following steps:

1. Import the necessary modules:

import cv2
import numpy as np
import matplotlib.pyplot as plt

2. Load the stereo rig calibration parameters:

data = np.load('../data/stereo/case1/stereo.npy').item()
Kl, Dl, Kr, Dr, R, T, img_size = data['Kl'], data['Dl'], data['Kr'], data['Dr'], \
                                 data['R'], data['T'], data['img_size']

3. Load the left and right test images:

left_img = cv2.imread('../data/stereo/case1/left14.png')
right_img ...