3D object detection in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding 3D Bounding Boxes

In 3D object detection, what does a 3D bounding box typically represent?

A A box that encloses the object in 3D space with position, size, and orientation

B A 2D rectangle drawn around the object in an image

C A point cloud representing the object's surface

D A heatmap showing object presence probability

💡 Hint

Think about how to describe an object’s location and shape in three dimensions.

A 3D bounding box defines the object's position, size (width, height, length), and orientation in 3D space, enclosing it tightly.

❓ Model Choice

intermediate

Choosing a Model for 3D Object Detection from Point Clouds

Which model architecture is best suited for detecting objects directly from raw 3D point cloud data?

A Recurrent Neural Network (RNN) for sequential data

B PointNet, which processes unordered point sets directly

C Convolutional Neural Network (CNN) designed for 2D images

D Transformer model for natural language processing

💡 Hint

Consider which model can handle unordered 3D points without converting to images.

PointNet is designed to process unordered 3D point clouds directly, making it suitable for 3D object detection from raw point data.

❓ Predict Output

advanced

Output Shape of 3D Object Detection Network

Given a 3D object detection network that outputs a tensor of shape (batch_size, num_anchors, 7), what does the last dimension of size 7 represent?

A Class probabilities for 7 object categories

B Coordinates (x, y), width, height, depth, and confidence score

C RGB color channels and depth value

D Coordinates (x, y, z), dimensions (w, h, l), and rotation angle

💡 Hint

Think about what parameters define a 3D bounding box and its orientation.

The 7 values typically represent the 3D box center (x, y, z), size (width, height, length), and rotation angle around an axis.

❓ Metrics

advanced

Evaluating 3D Object Detection Performance

Which metric is commonly used to evaluate the accuracy of 3D object detection models?

A 3D Intersection over Union (IoU) between predicted and ground truth boxes

B Mean Squared Error (MSE) of pixel intensities

C BLEU score for language translation

D Confusion matrix for binary classification

💡 Hint

Consider how to measure overlap between predicted and true 3D boxes.

3D IoU measures the volume overlap between predicted and ground truth bounding boxes, indicating detection accuracy.

🔧 Debug

expert

Debugging a 3D Object Detection Model with Poor Orientation Predictions

A 3D object detection model predicts bounding boxes with accurate positions and sizes but consistently wrong rotation angles. What is the most likely cause?

A The model uses 2D convolution layers instead of 3D convolutions

B The input point cloud is missing color information

C The loss function does not properly penalize rotation angle errors

D The batch size is too large causing overfitting

💡 Hint

Think about what part of training controls orientation accuracy.

If rotation errors are high but other box parameters are good, the loss function likely does not weight rotation angle errors enough or uses an unsuitable representation.

Practice

1. What is the main goal of 3D object detection in computer vision?

easy

A. To classify images into categories

B. To find and locate objects in three-dimensional space

C. To enhance image colors

D. To compress video files

Solution

1. Step 1: Understand 3D object detection purpose

   3D object detection aims to find objects and their positions in 3D space, unlike simple image classification.

2. Step 2: Compare options to definition

   Only To find and locate objects in three-dimensional space describes locating objects in 3D space, which matches the goal of 3D object detection.

3. Final Answer:

   To find and locate objects in three-dimensional space -> Option B

4. Quick Check:

   3D object detection = locating objects in 3D space [OK]

Hint: 3D detection means finding objects in 3D space, not just classifying [OK]

Common Mistakes:

• Confusing 3D detection with image classification
• Thinking it changes image colors
• Assuming it compresses data

2. Which of the following is the correct way to represent a 3D bounding box in code?

easy

A. A 2D rectangle with width and height only

B. A single number representing volume

C. A color code string like '#FF0000'

D. A list of 8 corner points with (x, y, z) coordinates

Solution

1. Step 1: Recall 3D bounding box structure

   A 3D bounding box is defined by its 8 corners in 3D space, each with (x, y, z) coordinates.

2. Step 2: Evaluate options

   Only A list of 8 corner points with (x, y, z) coordinates correctly describes this. Options A, B, and D do not represent 3D bounding boxes properly.

3. Final Answer:

   A list of 8 corner points with (x, y, z) coordinates -> Option D

4. Quick Check:

   3D box = 8 corners with (x,y,z) [OK]

Hint: 3D boxes need 8 corners, not just volume or 2D shapes [OK]

Common Mistakes:

• Using only 2D rectangles for 3D boxes
• Confusing volume with box representation
• Using color codes instead of coordinates

3. Given the following Python code snippet for a simple 3D object detection model output, what will be the printed prediction?

predictions = {'car': [1.2, 3.4, 0.5], 'pedestrian': [2.1, 1.0, 0.3]}
print(predictions['car'])

medium

A. [1.2, 3.4, 0.5]

B. [2.1, 1.0, 0.3]

C. 'car'

D. KeyError

Solution

1. Step 1: Understand dictionary access in Python

   Accessing predictions['car'] returns the value associated with the key 'car', which is the list [1.2, 3.4, 0.5].

2. Step 2: Confirm output of print statement

   The print statement outputs the list [1.2, 3.4, 0.5], so [1.2, 3.4, 0.5] is correct.

3. Final Answer:

   [1.2, 3.4, 0.5] -> Option A

4. Quick Check:

   Dictionary access by key returns its value [OK]

Hint: Dictionary[key] returns the value for that key in Python [OK]

Common Mistakes:

• Confusing keys and values
• Expecting a KeyError without reason
• Printing the key instead of the value

4. The following code attempts to calculate the center of a 3D bounding box but has an error. What is the error?

def center_of_box(corners):
    x = (corners[0][0] + corners[1][0] + corners[2][0] + corners[3][0]) / 4
    y = (corners[0][1] + corners[1][1] + corners[2][1] + corners[3][1]) / 4
    z = (corners[0][2] + corners[1][2] + corners[2][2] + corners[3][2]) / 4
    return (x, y, z)

box_corners = [(1,2,3), (3,2,3), (3,4,3), (1,4,3), (1,2,5), (3,2,5), (3,4,5), (1,4,5)]
print(center_of_box(box_corners))

medium

A. The box_corners list has incorrect data types

B. The function uses wrong indices for coordinates

C. Only 4 corners are averaged instead of all 8

D. The function returns a list instead of a tuple

Solution

1. Step 1: Analyze the function's averaging method

   The function averages only the first 4 corners, ignoring the last 4 corners of the 3D box.

2. Step 2: Understand 3D box center calculation

   To find the true center, all 8 corners must be averaged, so the function misses half the points.

3. Final Answer:

   Only 4 corners are averaged instead of all 8 -> Option C

4. Quick Check:

   Center needs all 8 corners averaged [OK]

Hint: Average all 8 corners for center, not just 4 [OK]

Common Mistakes:

• Averaging only part of the corners
• Mixing up coordinate indices
• Confusing tuples and lists (not an error here)

5. In a 3D object detection system for self-driving cars, which metric best measures how well the predicted 3D bounding boxes match the true boxes?

hard

A. Intersection over Union (IoU) in 3D space

B. Pixel accuracy on 2D images

C. Mean Squared Error of RGB colors

D. Number of detected objects only

Solution

1. Step 1: Understand evaluation metrics for 3D detection

   IoU measures overlap between predicted and true boxes, extended to 3D for volume overlap.

2. Step 2: Compare other options

   Pixel accuracy and color errors do not measure 3D box quality; counting objects ignores box accuracy.

3. Final Answer:

   Intersection over Union (IoU) in 3D space -> Option A

4. Quick Check:

   3D IoU = best metric for 3D box accuracy [OK]

Hint: Use 3D IoU to measure box overlap accuracy [OK]

Common Mistakes:

• Using 2D pixel accuracy for 3D boxes
• Confusing color error with box accuracy
• Ignoring box overlap quality