Why computer vision enables intelligent flight in Drone Programming - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load an image using OpenCV.

Drone Programming

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

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

Aresize

Bimread

Cimwrite

Dimshow

Attempts:

3 left

💡 Hint

Common Mistakes

Using imshow instead of imread, which only displays images.

The imread function loads an image from a file, which is essential for computer vision tasks in drones.

2fill in blank

medium

Complete the code to convert the image to grayscale for easier processing.

Drone Programming

gray_image = cv2.cvtColor(image, [1])

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

Acv2.COLOR_BGR2GRAY

Bcv2.COLOR_RGB2BGR

Ccv2.COLOR_GRAY2BGR

Dcv2.COLOR_BGR2RGB

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing color space conversions that do not produce grayscale images.

Converting to grayscale simplifies the image by removing color, which helps the drone focus on shapes and edges.

3fill in blank

hard

Fix the error in the code to detect edges using the Canny method.

Drone Programming

edges = cv2.Canny([1], 100, 200)

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

Aedges

Bimage

Cgray_image

Dcv2

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the original color image instead of the grayscale image.

The Canny edge detector requires a grayscale image as input, so we use gray_image.

4fill in blank

hard

Fill both blanks to create a dictionary of detected objects with their confidence scores.

Drone Programming

detected_objects = [1](object_name: confidence for object_name, confidence in [2].items() if confidence > 0.5)

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

Adict

Blist

Cdetections

Dset

Attempts:

3 left

💡 Hint

Common Mistakes

Using list or set instead of dict, or wrong variable name for detections.

We use dict to create a dictionary and detections as the source data holding object names and confidence scores.

5fill in blank

hard

Fill all three blanks to train a simple neural network model for flight path prediction.

Drone Programming

model = Sequential()
model.add(Dense([1], activation='relu', input_shape=([2],)))
model.add(Dense([3], activation='softmax'))

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

A64

B10

C100

D5

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up input shape and number of neurons, or wrong output layer size.

The first Dense layer has 64 neurons, input shape is 5 features, and output layer has 10 classes for prediction.