0
0
Computer Visionml~5 mins

IoU (Intersection over Union) in Computer Vision - Cheat Sheet & Quick Revision

Choose your learning style9 modes available
Recall & Review
beginner
What does IoU stand for in computer vision?
IoU stands for Intersection over Union. It is a metric used to measure the overlap between two areas, often between predicted and actual bounding boxes.
Click to reveal answer
beginner
How is IoU calculated?
IoU is calculated by dividing the area of overlap between the predicted bounding box and the ground truth bounding box by the area of their union.
Click to reveal answer
beginner
Why is IoU important in object detection?
IoU helps to evaluate how well the predicted bounding box matches the actual object. A higher IoU means better prediction accuracy.
Click to reveal answer
intermediate
What is a typical IoU threshold used to decide if a detection is correct?
A common IoU threshold is 0.5. If the IoU between predicted and ground truth boxes is above 0.5, the detection is considered correct.
Click to reveal answer
beginner
What happens to IoU if the predicted box and ground truth box do not overlap?
If there is no overlap, the intersection area is zero, so IoU is 0, indicating no match between predicted and actual boxes.
Click to reveal answer
What does the numerator in the IoU formula represent?
AThe area of overlap between predicted and ground truth boxes
BThe total area covered by both boxes
CThe area of the predicted box only
DThe area of the ground truth box only
If IoU = 1, what does it mean?
ANo overlap between boxes
BPartial overlap between boxes
CPerfect overlap between boxes
DBoxes are completely separate
Which IoU value usually indicates a good detection in object detection tasks?
A0.1
B0.9
C0.3
D0.5
What does the denominator in the IoU formula represent?
AArea of union of predicted and ground truth boxes
BArea of predicted box only
CArea of overlap
DArea of ground truth box only
If two boxes do not overlap at all, what is the IoU value?
A1
B0
C0.5
DUndefined
Explain what IoU (Intersection over Union) measures and why it is useful in object detection.
Think about how well predicted boxes match actual objects.
You got /4 concepts.
    Describe how you would calculate IoU given two bounding boxes.
    Focus on areas where boxes overlap and combine.
    You got /4 concepts.