Stereo vision concept in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main purpose of stereo vision in computer vision?

Stereo vision uses two cameras to mimic human eyes. What is the main goal of using stereo vision?

A To improve image brightness

B To estimate the depth of objects in a scene

C To detect edges more accurately

D To increase the color resolution of images

💡 Hint

Think about what having two slightly different views helps us understand about the scene.

Stereo vision helps calculate how far objects are by comparing two images from different viewpoints, similar to how our eyes perceive depth.

❓ Predict Output

intermediate

Output of disparity map calculation code snippet

Given the following Python code using OpenCV to compute a disparity map, what is the shape of the output disparity map?

Computer Vision

import cv2
left_img = cv2.imread('left.png', 0)
right_img = cv2.imread('right.png', 0)
stereo = cv2.StereoBM_create(numDisparities=16, blockSize=15)
disparity = stereo.compute(left_img, right_img)
print(disparity.shape)

A (height, width)

B (width, height)

C (height, width, 3)

D (width, height, 3)

💡 Hint

The disparity map is a single-channel image matching the input image size.

The disparity map has the same height and width as the input images but only one channel, so its shape is (height, width).

❓ Model Choice

advanced

Choosing the best stereo matching algorithm for real-time depth estimation

You want to implement stereo vision on a mobile robot that needs real-time depth estimation. Which stereo matching algorithm is best suited for this task?

A Semi-Global Matching (SGM) algorithm

B Graph Cuts algorithm

C Block Matching (BM) algorithm

D Dynamic Programming algorithm

💡 Hint

Consider the trade-off between speed and accuracy for real-time use.

Block Matching is faster and simpler, suitable for real-time applications, while others are more accurate but slower.

❓ Hyperparameter

advanced

Effect of increasing numDisparities in stereo matching

In stereo vision, what happens if you increase the numDisparities parameter in the block matching algorithm?

A The disparity search range increases, allowing detection of farther objects but increasing computation time

B The image resolution increases, improving depth accuracy

C The block size increases, improving noise resistance but reducing detail

D The number of cameras needed increases

💡 Hint

numDisparities controls how far the algorithm looks for matching points horizontally.

Increasing numDisparities expands the horizontal search range for matching pixels, which helps detect objects at greater distances but requires more computation.

❓ Metrics

expert

Evaluating stereo vision depth accuracy with error metrics

You have ground truth depth data and predicted depth from stereo vision. Which metric best measures the average absolute difference between predicted and true depth values?

A Peak Signal-to-Noise Ratio (PSNR)

B Root Mean Squared Error (RMSE)

C Structural Similarity Index (SSIM)

D Mean Absolute Error (MAE)

💡 Hint

Look for the metric that averages absolute differences without squaring.

MAE calculates the average absolute difference between predicted and true values, making it a straightforward measure of depth accuracy.

Practice

1. What is the main purpose of stereo vision in computer vision?

easy

A. To estimate the depth of objects by comparing two images

B. To enhance the color of images

C. To detect edges in a single image

D. To compress images for storage

Solution

1. Step 1: Understand stereo vision basics

   Stereo vision uses two images taken from slightly different viewpoints to find depth information.

2. Step 2: Identify the main goal

   The main goal is to estimate how far objects are by comparing their positions in the two images.

3. Final Answer:

   To estimate the depth of objects by comparing two images -> Option A

4. Quick Check:

   Stereo vision = Depth estimation [OK]

Hint: Stereo vision = depth from two images [OK]

Common Mistakes:

• Confusing stereo vision with color enhancement
• Thinking it works with only one image
• Mixing depth estimation with edge detection

2. Which of the following correctly describes 'disparity' in stereo vision?

easy

A. The difference in brightness between two images

B. The average color value of an image

C. The difference in pixel positions of the same point in two images

D. The total number of pixels in an image

Solution

1. Step 1: Define disparity in stereo vision

   Disparity is the horizontal difference in pixel positions of the same object point between the left and right images.

2. Step 2: Match the correct description

   It is not about brightness or color but about position difference to calculate depth.

3. Final Answer:

   The difference in pixel positions of the same point in two images -> Option C

4. Quick Check:

   Disparity = pixel position difference [OK]

Hint: Disparity = position difference between images [OK]

Common Mistakes:

• Confusing disparity with brightness or color
• Thinking disparity is total pixels count
• Mixing disparity with image resolution

3. Given two stereo images, the pixel of a point is at (x=150) in the left image and at (x=130) in the right image. What is the disparity value?

medium

A. 150

B. -20

C. 280

D. 20

Solution

1. Step 1: Calculate disparity from pixel positions

   Disparity = x_left - x_right = 150 - 130 = 20 pixels.

2. Step 2: Interpret the result

   Disparity is positive and represents how far the point shifted between images.

3. Final Answer:

   20 -> Option D

4. Quick Check:

   150 - 130 = 20 [OK]

Hint: Disparity = left x minus right x [OK]

Common Mistakes:

• Subtracting right from left incorrectly
• Using sum instead of difference
• Ignoring sign of disparity

4. You wrote code to compute disparity but always get zero values. What is the most likely error?

medium

A. Swapping the x and y coordinates in calculations

B. Using the same image for both left and right inputs

C. Using color images instead of grayscale

D. Calculating disparity as the sum of pixel positions

Solution

1. Step 1: Analyze zero disparity cause

   If both images are identical, the pixel positions match exactly, so disparity is zero everywhere.

2. Step 2: Check other options

   Swapping coordinates or color use won't cause all zero disparity; summing positions gives wrong values but not zero everywhere.

3. Final Answer:

   Using the same image for both left and right inputs -> Option B

4. Quick Check:

   Same images = zero disparity [OK]

Hint: Different images needed for disparity [OK]

Common Mistakes:

• Using identical images for stereo input
• Mixing x and y coordinates without correction
• Ignoring image color format effects

5. In a stereo vision system, if an object is very far away, how does its disparity value change and why?

hard

A. Disparity decreases because the pixel positions in both images become closer

B. Disparity increases because the object appears larger

C. Disparity stays the same regardless of distance

D. Disparity becomes negative because the object moves behind the cameras

Solution

1. Step 1: Understand disparity-distance relation

   Disparity is inversely related to distance; far objects have smaller disparity because their positions in both images are closer.

2. Step 2: Eliminate incorrect options

   Disparity does not increase with distance, nor does it become negative or stay constant.

3. Final Answer:

   Disparity decreases because the pixel positions in both images become closer -> Option A

4. Quick Check:

   Far object = small disparity [OK]

Hint: Farther objects have smaller disparity [OK]

Common Mistakes:

• Assuming disparity grows with distance
• Thinking disparity can be negative for far objects
• Believing disparity is constant