Why detection localizes objects in images in Computer Vision - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load an image using OpenCV.

Computer Vision

import cv2
image = cv2.[1]('image.jpg')

Drag options to blanks, or click blank then click option'

Aimwrite

Bimshow

Cimread

Dresize

Attempts:

3 left

💡 Hint

Common Mistakes

Using imshow instead of imread to load an image.

The imread function loads an image from a file into memory.

2fill in blank

medium

Complete the code to draw a rectangle around the detected object.

Computer Vision

cv2.rectangle(image, (x, y), (x + w, y + h), [1], 2)

Drag options to blanks, or click blank then click option'

A(255, 0, 0)

B(255, 255, 255)

C(0, 0, 255)

D(0, 255, 0)

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing red or blue which are other colors in BGR.

The color (0, 255, 0) represents green in BGR format, commonly used to highlight detected objects.

3fill in blank

hard

Fix the error in the code to correctly extract the bounding box coordinates.

Computer Vision

x, y, w, h = [1]

Drag options to blanks, or click blank then click option'

Adetected_object['bbox']

Bdetected_object['box']

Cdetected_object['coordinates']

Ddetected_object['location']

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect keys like 'box' or 'location' which do not exist.

The bounding box coordinates are stored under the key 'bbox' in the detection result dictionary.

4fill in blank

hard

Fill both blanks to create a dictionary of object labels and their confidence scores.

Computer Vision

results = {det['[1]']: det['[2]'] for det in detections}

Drag options to blanks, or click blank then click option'

Alabel

Bscore

Cbbox

Dclass

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'bbox' or 'class' which are not the correct keys for label or score.

The dictionary maps each detected object's label to its score, representing confidence.

5fill in blank

hard

Fill all three blanks to filter detections with confidence above 0.5 and create a list of bounding boxes.

Computer Vision

filtered_boxes = [det['[1]'] for det in detections if det['[2]'] [3] 0.5]

Drag options to blanks, or click blank then click option'

Abbox

Bscore

C>

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' or wrong keys for bounding boxes or scores.

This code selects bounding boxes where the detection score is greater than 0.5, meaning confident detections.