Depth, Recognition, and Evaluation

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 stereo vision and depth?A. Object detection usually predicts boxes, classes, and confidence scores.B. For a simplified rectified stereo pair, depth equals focal length times camera baseline divided by disparity.C. Precision asks what fraction of accepted detections are correct.D. Choose the split unit according to the intended deployment.

2. Which explanation matches detection and segmentation in practice?A. Object detection usually predicts boxes, classes, and confidence scores.B. For a simplified rectified stereo pair, depth equals focal length times camera baseline divided by disparity.C. Precision asks what fraction of accepted detections are correct.D. Choose the split unit according to the intended deployment.

3. Which explanation matches overlap, precision, and recall?A. For a simplified rectified stereo pair, depth equals focal length times camera baseline divided by disparity.B. Object detection usually predicts boxes, classes, and confidence scores.C. Choose the split unit according to the intended deployment.D. Precision asks what fraction of accepted detections are correct.

4. Choose an output for counting animals, measuring their visible silhouettes, and distinguishing overlapping individuals.A. Eight hundred times 0.1 divided by 40 equals two meters.B. IoU is 30 divided by 50, which equals 0.6.C. Boxes may support counting. Pixel masks support visible silhouettes. Instance masks distinguish individual objects when the labeling and model support that task.D. Reserve one or more complete camera locations for testing, and use separate training and validation locations or groups for development when the available data permits.

5. Design a split for a system intended to work on a camera location it has never seen.A. Eight hundred times 0.1 divided by 40 equals two meters.B. Reserve one or more complete camera locations for testing, and use separate training and validation locations or groups for development when the available data permits.C. Boxes may support counting. Pixel masks support visible silhouettes. Instance masks distinguish individual objects when the labeling and model support that task.D. IoU is 30 divided by 50, which equals 0.6.

Review this module from its first lesson →

Depth, Recognition, and Evaluation

Your result