Question 1 of 20

In the pinhole camera model, homogeneous coordinates allow us to:

Question 2 of 20

Camera intrinsic matrix K encodes:

Question 3 of 20

Harris corner detector looks for points where:

Question 4 of 20

Lowe's ratio test when matching SIFT descriptors rejects matches when:

Question 5 of 20

RANSAC is used in geometric vision primarily to:

Question 6 of 20

Radial lens distortion causes straight lines in the scene to:

Question 7 of 20

In rectified stereo, corresponding points lie:

Question 8 of 20

Depth Z from disparity d (baseline B, focal length f) scales as:

Question 9 of 20

A homography H maps points between two views when:

Question 10 of 20

ORB descriptors are popular in real-time pipelines because:

Question 11 of 20

Zhang's calibration method uses multiple views of a checkerboard to:

Question 12 of 20

Textureless regions are hard for stereo matching because:

Question 13 of 20

The essential matrix E relates corresponding points in:

Question 14 of 20

Scale-invariant feature detectors address the problem that:

Question 15 of 20

Wider stereo baseline generally:

Question 16 of 20

The principal point in K is:

Question 17 of 20

Increasing RANSAC iterations is needed when:

Question 18 of 20

Epipolar geometry constrains matching so that:

Question 19 of 20

Subpixel disparity refinement improves depth maps by:

Question 20 of 20

Reprojection error in calibration measures: