18. Undistort and Transform

Undistort and Transform Perspective

Here's a tricky quiz for you! You have now seen how to find corners, calibrate your camera, undistort an image, and apply a perspective transform. Now it's your chance to perform all these steps on an image. In the last quiz you calibrated the camera, so here I'm giving you the camera matrix, mtx , and the distortion coefficients dist to start with.

Your goal is to generate output like the image shown above. To do that, you need to write a function that takes your distorted image as input and completes the following steps:

  • Undistort the image using cv2.undistort() with mtx and dist
  • Convert to grayscale
  • Find the chessboard corners
  • Draw corners
  • Define 4 source points (the outer 4 corners detected in the chessboard pattern)
  • Define 4 destination points (must be listed in the same order as src points!)
  • Use cv2.getPerspectiveTransform() to get M , the transform matrix
  • use cv2.warpPerspective() to apply M and warp your image to a top-down view

HINT: Source points are the x and y pixel values of any four corners on your chessboard, you can extract these from the corners array output from cv2.findChessboardCorners() . Your destination points are the x and y pixel values of where you want those four corners to be mapped to in the output image.

If you run into any errors as you run your code, please refer to the Examples of Useful Code section in the previous video and make sure that your code syntax matches up! For this example, please also refer back to the examples in the Calibrating Your Camera video. You can also download the distortion pickle file and test image used in the below quiz if you'd like to run the below code on your own machine.

Start Quiz: 

import pickle
import cv2
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg

# Read in the saved camera matrix and distortion coefficients
# These are the arrays you calculated using cv2.calibrateCamera()
dist_pickle = pickle.load( open( "wide_dist_pickle.p", "rb" ) )
mtx = dist_pickle["mtx"]
dist = dist_pickle["dist"]

# Read in an image
img = cv2.imread('test_image2.png')
nx = 8 # the number of inside corners in x
ny = 6 # the number of inside corners in y

# MODIFY THIS FUNCTION TO GENERATE OUTPUT 
# THAT LOOKS LIKE THE IMAGE ABOVE
def corners_unwarp(img, nx, ny, mtx, dist):
    # Pass in your image into this function
    # Write code to do the following steps
    # 1) Undistort using mtx and dist
    # 2) Convert to grayscale
    # 3) Find the chessboard corners
    # 4) If corners found: 
            # a) draw corners
            # b) define 4 source points src = np.float32([[,],[,],[,],[,]])
                 #Note: you could pick any four of the detected corners 
                 # as long as those four corners define a rectangle
                 #One especially smart way to do this would be to use four well-chosen
                 # corners that were automatically detected during the undistortion steps
                 #We recommend using the automatic detection of corners in your code
            # c) define 4 destination points dst = np.float32([[,],[,],[,],[,]])
            # d) use cv2.getPerspectiveTransform() to get M, the transform matrix
            # e) use cv2.warpPerspective() to warp your image to a top-down view
    #delete the next two lines
    M = None
    warped = np.copy(img) 
    return warped, M

top_down, perspective_M = corners_unwarp(img, nx, ny, mtx, dist)
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(img)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(top_down)
ax2.set_title('Undistorted and Warped Image', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)

Next Concept