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.