# A short quiz on computational stereo

1. The disparity of a nearby object is:

• the same as that of a distant object
• greater than that of a distant object

• less than that of a distant object
• indeterminate
2. What is disparity?

• The distance to an object in an image
• The foreshortening of an object with distance
• The discrepancy in the apparent position of an object in the left and right images

• The relative size of the same object when it is nearby and far away
3. As the baseline, the distance between the cameras, increases, what happens to the disparity?

• The product of disparity and focal length stays the same
• The disparity decreases
• The disparity increases

• The disparity stays the same
4. In a camera, the incoming light is focussed onto:

• the lens
• the front focal plane
• the back focal plane

• the optical axis
5. Why is a pin-hole camera rarely used in practice?

• Only distant objects are in focus
• The pin-hole is always too large for an image to be made
• Only nearby objects are in focus
• Exposure times are long

6. Which of the following is not an assumption we have made in considering computational stereo?

• The object is stationary

• The optical axes of the cameras are parallel
• The images are captured by both cameras simultaneously
• The cameras are identical
7. Which of the following equations determines the distance to an object $Z$ given its disparity $D$, baseline $B$ and focal length $f$?

• $Z = B / fD$
• $Z = fD / B$
• $Z = D / fB$
• $Z = fB / D$

8. In order to use computational stereo, we must find:

• The location of the same feature in the left and right images

• Different pixels in the left and right images
• The same pixel in the left and right images
• The location of different features in the left and right images
9. How does disparity vary with distance?

• Disparity is inversely proportional to the square of distance
• Disparity is proportional to the square of distance
• Disparity is proportional to distance
• Disparity is inversely proportional to distance

10. Which of the following is usually the most important source of error in computational stereo?

• Failing to align the optical axes to be parallel

• Locating the centre of the image
• Having dissimilar cameras
• Measuring the baseline inaccurately
11.