Video Tracking

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 detect objects frame by frame?A. Data association links a new detection to a previous track using motion and appearance evidence.B. Framewise detections provide candidate boxes and scores but no persistent identity.C. A tracker can maintain a tentative state through short occlusions and reconnect later evidence.D. Tracking metrics include detection coverage and identity consistency, which measure different errors.

2. Which explanation matches associate detections through time?A. Data association links a new detection to a previous track using motion and appearance evidence.B. Framewise detections provide candidate boxes and scores but no persistent identity.C. A tracker can maintain a tentative state through short occlusions and reconnect later evidence.D. Tracking metrics include detection coverage and identity consistency, which measure different errors.

3. Which explanation matches recover from occlusion and missed frames?A. Framewise detections provide candidate boxes and scores but no persistent identity.B. Data association links a new detection to a previous track using motion and appearance evidence.C. Tracking metrics include detection coverage and identity consistency, which measure different errors.D. A tracker can maintain a tentative state through short occlusions and reconnect later evidence.

4. For associate detections through time, which result or action fits this practical case: Two cars cross in the camera view.A. Keep the box coordinates and timestamps for cars in consecutive frames.B. Flag uncertain identity until the hidden car becomes visible again.C. Compare predicted positions and visual similarity before assigning track IDs.D. Review one identity switch after two cars cross, even if every car was detected.

5. For evaluate tracks and identity switches, which result or action fits this practical case: A tracker counts vehicles well but keeps swapping their names.A. Keep the box coordinates and timestamps for cars in consecutive frames.B. Review one identity switch after two cars cross, even if every car was detected.C. Compare predicted positions and visual similarity before assigning track IDs.D. Flag uncertain identity until the hidden car becomes visible again.

Review this module from its first lesson →

Video Tracking

Your result