IoU (Intersection over Union) in Computer Vision - Model Pipeline Trace

Model Pipeline - IoU (Intersection over Union)

This pipeline calculates the Intersection over Union (IoU) metric to measure how well predicted bounding boxes match the true boxes in object detection tasks.

Data Flow - 4 Stages

1Input bounding boxes

N predicted boxes and N true boxes→Receive predicted and true bounding boxes coordinates→N predicted boxes and N true boxes

Predicted box: [x1=30, y1=40, x2=70, y2=80], True box: [x1=50, y1=60, x2=90, y2=100]

↓

2Calculate intersection

N predicted boxes and N true boxes→Find overlapping area between predicted and true boxes→N intersection areas

Intersection box: [x1=50, y1=60, x2=70, y2=80], area=400

↓

3Calculate union

N predicted boxes and N true boxes→Calculate total area covered by both boxes minus intersection→N union areas

Union area = predicted area + true area - intersection area = 1600 + 1600 - 400 = 2800

↓

4Compute IoU

N intersection areas and N union areas→Divide intersection area by union area for each box pair→N IoU scores between 0 and 1

IoU = 400 / 2800 = 0.1429

Training Trace - Epoch by Epoch

Loss
1.0 |***************
0.8 |************  
0.6 |********     
0.4 |******       
0.2 |***          
0.0 +------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.75	0.40	Initial IoU scores are low, model starts learning bounding box locations
2	0.60	0.55	IoU improves as predicted boxes better overlap true boxes
3	0.45	0.70	Model predicts bounding boxes closer to ground truth, IoU increases
4	0.35	0.80	Good overlap achieved, IoU scores near 0.8 on average
5	0.30	0.85	Model converges with high IoU, bounding boxes well aligned

Prediction Trace - 4 Layers

Layer 1: Input predicted and true boxes

Layer 2: Calculate intersection box

Layer 3: Calculate union area

Layer 4: Compute IoU score

Model Quiz - 3 Questions

What does a higher IoU score indicate about predicted and true bounding boxes?

A They are farther apart

B They overlap more closely

C They have no overlap

D They have the same area

Key Insight

IoU is a key metric in object detection that quantifies how well predicted boxes match true boxes by measuring their overlap. Higher IoU means better predictions and is used to guide model training and evaluation.

Practice

1. What does IoU (Intersection over Union) measure in computer vision?

easy

A. The overlap between two bounding boxes

B. The distance between two points

C. The brightness of an image

D. The number of pixels in an image

Solution

1. Step 1: Understand IoU definition

   IoU measures how much two areas overlap compared to their total combined area.

2. Step 2: Identify what IoU compares

   It compares two bounding boxes or regions to see how well they match.

3. Final Answer:

   The overlap between two bounding boxes -> Option A

4. Quick Check:

   IoU = Overlap / Union [OK]

Hint: IoU = Overlap area divided by combined area [OK]

Common Mistakes:

• Confusing IoU with distance metrics
• Thinking IoU measures brightness or color
• Assuming IoU can be greater than 1

2. Which of the following is the correct formula for IoU between two boxes A and B?

easy

A. Area(A) + Area(B)

B. Area(A ∩ B) / Area(A ∪ B)

C. Area(A ∪ B) / Area(A ∩ B)

D. Area(A) - Area(B)

Solution

1. Step 1: Recall IoU formula

   IoU is defined as the intersection area divided by the union area of two boxes.

2. Step 2: Match formula to options

   Area(A ∩ B) / Area(A ∪ B) correctly shows IoU = Area of intersection over area of union.

3. Final Answer:

   Area(A ∩ B) / Area(A ∪ B) -> Option B

4. Quick Check:

   IoU = Intersection / Union [OK]

Hint: IoU = Intersection area ÷ Union area [OK]

Common Mistakes:

• Swapping numerator and denominator
• Adding areas instead of dividing
• Subtracting areas instead of dividing

3. Given two bounding boxes: Box A with area 20, Box B with area 30, and their intersection area is 10, what is the IoU?

medium

A. 0.25

B. 0.33

C. 0.5

D. 0.67

Solution

1. Step 1: Calculate union area

   Union = Area(A) + Area(B) - Intersection = 20 + 30 - 10 = 40.

2. Step 2: Calculate IoU

   IoU = Intersection / Union = 10 / 40 = 0.25.

3. Final Answer:

   0.25 -> Option A

4. Quick Check:

   IoU = 10/40 = 0.25 [OK]

Hint: IoU = Intersection ÷ (A + B - Intersection) [OK]

Common Mistakes:

• Forgetting to subtract intersection in union
• Using sum of areas as union
• Mixing up intersection and union values

4. Consider this Python code to compute IoU:

def iou(area_a, area_b, intersection):
    union = area_a + area_b + intersection
    return intersection / union

print(iou(15, 25, 5))

What is the error in this code?

medium

A. Function should return union instead of IoU

B. Intersection should be added twice in union

C. Division should be union divided by intersection

D. Union is calculated incorrectly by adding intersection instead of subtracting

Solution

1. Step 1: Check union calculation

   Union should be area_a + area_b - intersection, not plus intersection.

2. Step 2: Identify impact on IoU

   Adding intersection inflates union, making IoU smaller than correct value.

3. Final Answer:

   Union is calculated incorrectly by adding intersection instead of subtracting -> Option D

4. Quick Check:

   Union = A + B - Intersection [OK]

Hint: Union = sum of areas minus intersection [OK]

Common Mistakes:

• Adding intersection instead of subtracting
• Swapping numerator and denominator
• Returning union instead of IoU

5. You have two predicted bounding boxes and one ground truth box. Box1 IoU with ground truth is 0.6, Box2 IoU is 0.4. If the threshold for a correct detection is 0.5, which box is considered a correct detection and why?

hard

A. Both boxes are correct because any IoU > 0 counts

B. Only Box2 is correct because it has lower IoU

C. Only Box1 is correct because its IoU is above 0.5

D. Neither box is correct because threshold is 0.7

Solution

1. Step 1: Understand IoU threshold meaning

   Threshold 0.5 means IoU must be at least 0.5 to count as correct detection.

2. Step 2: Compare IoU values to threshold

   Box1 IoU = 0.6 > 0.5 (correct), Box2 IoU = 0.4 < 0.5 (incorrect).

3. Final Answer:

   Only Box1 is correct because its IoU is above 0.5 -> Option C

4. Quick Check:

   IoU ≥ 0.5 means correct detection [OK]

Hint: IoU must meet threshold to be correct detection [OK]

Common Mistakes:

• Ignoring threshold and accepting all IoUs
• Confusing higher IoU as incorrect
• Using wrong threshold value