Stereo vision concept in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load two stereo images using OpenCV.

Computer Vision

import cv2

left_image = cv2.imread([1])
right_image = cv2.imread('right.jpg')

Drag options to blanks, or click blank then click option'

A'leftimage.jpg'

B'left_image.jpg'

C'left.jpg'

D'left.png'

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong filename or extension.

Forgetting quotes around the filename.

The left stereo image filename is 'left.jpg'. We use cv2.imread() to load it.

2fill in blank

medium

Complete the code to convert the stereo images to grayscale.

Computer Vision

left_gray = cv2.cvtColor(left_image, [1])
right_gray = cv2.cvtColor(right_image, cv2.COLOR_BGR2GRAY)

Drag options to blanks, or click blank then click option'

Acv2.COLOR_BGR2RGB

Bcv2.COLOR_BGR2GRAY

Ccv2.COLOR_RGB2GRAY

Dcv2.COLOR_GRAY2BGR

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong color conversion code.

Confusing RGB and BGR color orders.

To convert a color image to grayscale, use cv2.COLOR_BGR2GRAY.

3fill in blank

hard

Fix the error in the code to compute disparity map using StereoBM.

Computer Vision

stereo = cv2.StereoBM_create(numDisparities=16, blockSize=[1])
disparity = stereo.compute(left_gray, right_gray)

Drag options to blanks, or click blank then click option'

A5

B15

C21

D7

Attempts:

3 left

💡 Hint

Common Mistakes

Using an even number for blockSize.

Using a blockSize too small or too large.

The blockSize must be an odd number between 5 and 255. 7 is a valid choice.

4fill in blank

hard

Fill both blanks to normalize and display the disparity map using OpenCV.

Computer Vision

disp_norm = cv2.normalize(disparity, None, [1], [2], cv2.NORM_MINMAX)
cv2.imshow('Disparity', disp_norm)
cv2.waitKey(0)
cv2.destroyAllWindows()

Drag options to blanks, or click blank then click option'

A0

B255

C-1

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using negative values for normalization range.

Confusing min and max values.

Normalization scales disparity to 0-255 for display.

5fill in blank

hard

Fill all three blanks to create a depth map from disparity and focal length.

Computer Vision

focal_length = 0.8  # in meters
baseline = 0.1       # distance between cameras in meters
depth_map = [1] * baseline / (disparity.astype(float) + [2])
depth_map[disparity == 0] = [3]

Drag options to blanks, or click blank then click option'

Afocal_length

B1e-6

C0

Dnp.inf

Attempts:

3 left

💡 Hint

Common Mistakes

Dividing by zero causing errors.

Not handling zero disparity pixels.

Depth = focal_length * baseline / disparity. Add a small number to avoid division by zero. Set depth to infinity where disparity is zero.