Features and Motion

Five questions. Choose one answer for each, then submit to see your score and explanations.

The practice target is 80%. You can retry as often as you like, and every lesson stays accessible.

You can practice as a guest. Sign in before starting an attempt to save your scores.

1. Which explanation matches corners, features, and descriptors?A. A feature detector answers where to look.B. Nearest-neighbor comparison finds descriptors that look similar.C. Many classical methods assume that corresponding points keep approximately the same brightness and that motion can be estimated over a local neighborhood.D. A tracker often predicts where an object should move, then compares that prediction with new detections.

2. Which explanation matches match images without trusting every match?A. A feature detector answers where to look.B. Many classical methods assume that corresponding points keep approximately the same brightness and that motion can be estimated over a local neighborhood.C. A tracker often predicts where an object should move, then compares that prediction with new detections.D. Nearest-neighbor comparison finds descriptors that look similar.

3. Which explanation matches optical flow: motion in the image?A. A feature detector answers where to look.B. Nearest-neighbor comparison finds descriptors that look similar.C. Many classical methods assume that corresponding points keep approximately the same brightness and that motion can be estimated over a local neighborhood.D. A tracker often predicts where an object should move, then compares that prediction with new detections.

4. Why should accepted matches be spread across an image when estimating a global warp?A. The blank surface may have too few features. The repeated pattern may have many features but ambiguous correspondences.B. Broad coverage constrains the mapping over a larger region. A small cluster can leave the rest of the image poorly constrained.C. Optical flow follows apparent image changes. A reflection can move across the surface and violate the assumption that appearance stays attached to a physical point.D. Measure drift, lost observations, identity switches, and time per frame. Do not summarize all of them as a single success count.

5. Create a short tracking test with clear motion, partial occlusion, and two similar objects crossing. Record different error types separately.A. Measure drift, lost observations, identity switches, and time per frame. Do not summarize all of them as a single success count.B. The blank surface may have too few features. The repeated pattern may have many features but ambiguous correspondences.C. Broad coverage constrains the mapping over a larger region. A small cluster can leave the rest of the image poorly constrained.D. Optical flow follows apparent image changes. A reflection can move across the surface and violate the assumption that appearance stays attached to a physical point.

Review this module from its first lesson →

Features and Motion

Your result