CV applications (autonomous driving, medical, retail) in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Key CV Tasks in Autonomous Driving

Which of the following computer vision tasks is MOST critical for detecting pedestrians and other vehicles in autonomous driving?

A Image segmentation to colorize the image for aesthetic purposes

B Image classification to label the entire scene as safe or unsafe

C Object detection to locate and identify multiple objects in the scene

D Style transfer to change the weather conditions in images

💡 Hint

Think about what helps the car know where other objects are around it.

Object detection finds and labels multiple objects with their locations, which is essential for safe navigation in autonomous driving.

❓ Predict Output

intermediate

Output Shape of Medical Image Segmentation Model

Given a 3D medical image input of shape (1, 128, 128, 64, 1) (batch, height, width, depth, channels), what is the output shape of a 3D U-Net model that predicts a binary mask for the same volume?

Computer Vision

import tensorflow as tf
input_shape = (128, 128, 64, 1)
inputs = tf.keras.Input(shape=input_shape)
# Assume model outputs a binary mask with same spatial dims
outputs = tf.keras.layers.Conv3D(1, 1, activation='sigmoid')(inputs)
model = tf.keras.Model(inputs, outputs)
print(model.output_shape)

A (None, 128, 128, 64)

B (None, 128, 128, 64, 1)

C (None, 1, 1, 1, 1)

D (None, 128, 128, 64, 2)

💡 Hint

Check the Conv3D output filters and input shape.

The Conv3D layer with 1 filter outputs a volume with the same spatial dimensions and 1 channel, matching the input shape except batch size.

❓ Model Choice

advanced

Best Model for Retail Shelf Product Recognition

Which model architecture is BEST suited for recognizing and localizing multiple products on a retail shelf image with many overlapping items?

A YOLOv5 for real-time object detection

B Autoencoder for image compression

C ResNet50 for image classification

D GAN for image generation

💡 Hint

Look for a model that can find many objects quickly.

YOLOv5 is designed for fast and accurate object detection, ideal for detecting many products in cluttered retail images.

❓ Hyperparameter

advanced

Choosing Hyperparameters for Autonomous Driving Segmentation

When training a semantic segmentation model for road scene understanding in autonomous driving, which hyperparameter adjustment MOST improves the model's ability to detect small objects like traffic signs?

A Increase batch size to 128 for faster training

B Remove dropout layers to prevent underfitting

C Reduce input image resolution to speed up training

D Use a smaller learning rate and deeper network layers

💡 Hint

Small objects need detailed features and careful training.

A smaller learning rate helps the model learn fine details steadily, and deeper layers capture complex features needed for small object detection.

❓ Metrics

expert

Evaluating Medical Image Segmentation Quality

A medical image segmentation model outputs masks for tumor regions. Which metric BEST measures the overlap quality between predicted and true tumor masks?

A Dice coefficient (F1 score for masks)

B Mean Squared Error between predicted and true masks

C Accuracy - percentage of correctly classified pixels

D Precision - ratio of true positives to predicted positives

💡 Hint

Look for a metric that balances false positives and false negatives in segmentation.

Dice coefficient measures overlap between two sets, balancing false positives and negatives, making it ideal for segmentation quality.

Practice

1. Which of the following is a common use of computer vision in autonomous driving?

easy

A. Detecting pedestrians and other vehicles on the road

B. Managing inventory in a warehouse

C. Analyzing blood samples in a lab

D. Recommending products to online shoppers

Solution

1. Step 1: Understand autonomous driving needs

   Autonomous cars need to see and understand their surroundings to drive safely.

2. Step 2: Match computer vision tasks to driving

   Detecting pedestrians and vehicles helps the car avoid accidents and navigate roads.

3. Final Answer:

   Detecting pedestrians and other vehicles on the road -> Option A

4. Quick Check:

   Autonomous driving = detecting road objects [OK]

Hint: Autonomous driving means seeing road and traffic [OK]

Common Mistakes:

• Confusing retail or medical uses with driving
• Thinking CV only works for product tracking
• Mixing up lab analysis with driving tasks

2. Which Python library is commonly used for image processing in computer vision tasks?

easy

A. NumPy

B. Pandas

C. OpenCV

D. Matplotlib

Solution

1. Step 1: Identify libraries for image processing

   OpenCV is designed specifically for computer vision and image tasks.

2. Step 2: Compare other libraries

   NumPy handles arrays, Pandas handles tables, Matplotlib is for plotting, but OpenCV processes images.

3. Final Answer:

   OpenCV -> Option C

4. Quick Check:

   Image processing library = OpenCV [OK]

Hint: OpenCV is the go-to for CV image tasks [OK]

Common Mistakes:

• Choosing NumPy for image processing only
• Confusing Pandas with image libraries
• Picking Matplotlib which is for plotting

3. What will the following Python code output when using a pre-trained model to classify an image in a retail store?

import cv2
model = cv2.dnn.readNetFromONNX('product_classifier.onnx')
image = cv2.imread('shelf.jpg')
blob = cv2.dnn.blobFromImage(image, 1/255.0, (224,224), swapRB=True)
model.setInput(blob)
predictions = model.forward()
print(predictions.argmax())

medium

A. The raw image pixels as a list

B. The size of the input image

C. An error because the model file is missing

D. The index of the most likely product class detected

Solution

1. Step 1: Understand the code flow

   The code loads a model, prepares the image, runs prediction, and prints the class with highest score.

2. Step 2: Interpret the output

   predictions.argmax() returns the index of the class with the highest confidence, meaning the predicted product.

3. Final Answer:

   The index of the most likely product class detected -> Option D

4. Quick Check:

   Model prediction = class index [OK]

Hint: argmax gives highest scoring class index [OK]

Common Mistakes:

• Thinking it prints raw pixels
• Assuming it prints image size
• Expecting an error without checking file presence

4. A medical imaging model is not detecting tumors correctly. The code snippet is:

image = cv2.imread('scan.png')
blob = cv2.dnn.blobFromImage(image, scalefactor=1.0, size=(224,224))
model.setInput(blob)
pred = model.forward()

What is the likely issue causing poor detection?

medium

A. The image is not resized before blob creation

B. The scalefactor should normalize pixel values (e.g., 1/255.0)

C. The model input is missing color channel swap

D. The model file is not loaded

Solution

1. Step 1: Check image preprocessing

   Pixel values usually need normalization (scaling to 0-1) for good model input.

2. Step 2: Identify scalefactor problem

   Using scalefactor=1.0 keeps pixel values 0-255, which can confuse the model expecting 0-1.

3. Final Answer:

   The scalefactor should normalize pixel values (e.g., 1/255.0) -> Option B

4. Quick Check:

   Normalize pixels for model input [OK]

Hint: Normalize pixels with scalefactor 1/255.0 [OK]

Common Mistakes:

• Ignoring pixel normalization
• Assuming resizing alone fixes issues
• Forgetting color channel order matters

5. In an autonomous driving system, how can computer vision help improve safety during night driving?

hard

A. By using infrared cameras to detect pedestrians in low light

B. By increasing the car's speed automatically

C. By disabling sensors to save power

D. By only relying on GPS data

Solution

1. Step 1: Understand night driving challenges

   Low light makes it hard for normal cameras to see pedestrians and obstacles.

2. Step 2: Identify CV solution for low light

   Infrared cameras capture heat signatures, helping detect people even in darkness.

3. Final Answer:

   By using infrared cameras to detect pedestrians in low light -> Option A

4. Quick Check:

   Infrared helps see in dark [OK]

Hint: Infrared cameras detect heat at night [OK]

Common Mistakes:

• Thinking speed increase improves safety
• Disabling sensors reduces safety
• Relying only on GPS ignores vision needs