IoU (Intersection over Union) in Computer Vision

Introduction

IoU helps us measure how much two shapes overlap. It tells us how well a predicted area matches the true area.

When checking how well a model detects objects in images.

When comparing predicted boxes with real boxes in object detection.

When deciding if two areas are similar enough to count as a match.

When evaluating segmentation masks in images.

When filtering overlapping predictions to keep the best one.

Syntax

Computer Vision

def iou(box1, box2):
    # box format: [x1, y1, x2, y2]
    x_left = max(box1[0], box2[0])
    y_top = max(box1[1], box2[1])
    x_right = min(box1[2], box2[2])
    y_bottom = min(box1[3], box2[3])

    if x_right <= x_left or y_bottom <= y_top:
        return 0.0

    intersection_area = (x_right - x_left) * (y_bottom - y_top)

    box1_area = (box1[2] - box1[0]) * (box1[3] - box1[1])
    box2_area = (box2[2] - box2[0]) * (box2[3] - box2[1])

    iou_value = intersection_area / float(box1_area + box2_area - intersection_area)
    return iou_value

Boxes are usually given as [x1, y1, x2, y2], where (x1, y1) is top-left and (x2, y2) is bottom-right corner.

IoU value ranges from 0 (no overlap) to 1 (perfect overlap).

Examples

Calculates IoU for two overlapping boxes.

Computer Vision

boxA = [1, 1, 4, 4]
boxB = [2, 2, 5, 5]
iou_score = iou(boxA, boxB)
print(f"IoU: {iou_score:.2f}")

Calculates IoU for two boxes that do not overlap, result should be 0.

Computer Vision

boxA = [0, 0, 2, 2]
boxB = [3, 3, 5, 5]
iou_score = iou(boxA, boxB)
print(f"IoU: {iou_score:.2f}")

Sample Model

This program defines a function to calculate IoU and tests it on two pairs of boxes: one overlapping and one non-overlapping.

Computer Vision

def iou(box1, box2):
    x_left = max(box1[0], box2[0])
    y_top = max(box1[1], box2[1])
    x_right = min(box1[2], box2[2])
    y_bottom = min(box1[3], box2[3])

    if x_right <= x_left or y_bottom <= y_top:
        return 0.0

    intersection_area = (x_right - x_left) * (y_bottom - y_top)

    box1_area = (box1[2] - box1[0]) * (box1[3] - box1[1])
    box2_area = (box2[2] - box2[0]) * (box2[3] - box2[1])

    iou_value = intersection_area / float(box1_area + box2_area - intersection_area)
    return iou_value

# Example boxes
box1 = [1, 1, 4, 4]
box2 = [2, 2, 5, 5]
box3 = [0, 0, 2, 2]
box4 = [3, 3, 5, 5]

print(f"IoU between box1 and box2: {iou(box1, box2):.2f}")
print(f"IoU between box3 and box4: {iou(box3, box4):.2f}")

Important Notes

IoU is a key metric in object detection tasks to check prediction quality.

If boxes do not overlap, IoU is zero, meaning no common area.

Higher IoU means better match between predicted and true boxes.

Summary

IoU measures overlap between two boxes or areas.

It is used to evaluate how well predictions match reality.

IoU values range from 0 (no overlap) to 1 (perfect overlap).

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