Color-based tracking in Drone Programming - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of color detection thresholding

What is the output of the following code snippet that processes an image to detect a red object using HSV color space thresholding?

Drone Programming

import cv2
import numpy as np

# Create a 3x3 image with one red pixel in HSV
image = np.zeros((3,3,3), dtype=np.uint8)
image[1,1] = [0, 255, 255]  # HSV red

# Define red color range in HSV
lower_red = np.array([0, 100, 100])
upper_red = np.array([10, 255, 255])

# Threshold the image
mask = cv2.inRange(image, lower_red, upper_red)

print(mask)

A

[[  0   0   0]
 [  0 255   0]
 [  0   0   0]]

B

[[255 255 255]
 [255 255 255]
 [255 255 255]]

C

[[0 0 0]
 [0 0 0]
 [0 0 0]]

D

[[0 0 0]
 [255 0 255]
 [0 0 0]]

💡 Hint

Remember that cv2.inRange returns 255 for pixels within the range and 0 otherwise.

The pixel at position (1,1) is red in HSV and falls within the threshold, so mask at that position is 255, others are 0.

🧠 Conceptual

intermediate

Understanding color space conversion

Why do drone programs often convert camera images from BGR to HSV color space for color-based tracking?

A Because HSV images have fewer pixels, improving performance.

B Because HSV separates color information from brightness, making color detection more robust to lighting changes.

C Because BGR images are always grayscale and cannot detect colors.

D Because BGR color space is not supported by drone cameras.

💡 Hint

Think about how lighting affects color detection.

HSV separates hue (color) from saturation and value (brightness), so detecting colors is easier and less sensitive to light changes.

🔧 Debug

advanced

Identify the error in color tracking code

What error will this drone tracking code raise when run?

Drone Programming

import cv2
import numpy as np

frame = np.zeros((5,5,3), dtype=np.uint8)
frame[2,2] = [0, 0, 255]  # Red in BGR

hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
lower_blue = np.array([110,50,50])
upper_blue = np.array([130,255,255])

mask = cv2.inRange(hsv, lower_blue, upper_blue)

contours, _ = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

print(contours[0])

A TypeError: 'NoneType' object is not iterable

B SyntaxError: invalid syntax

C No error, prints contour points

D IndexError: list index out of range

💡 Hint

Check what happens if no blue pixels are detected.

Since the image has only a red pixel, the blue mask is empty, so contours list is empty and accessing contours[0] causes IndexError.

📝 Syntax

advanced

Find the syntax error in color mask creation

Which option contains the correct syntax to create a mask for green color in HSV using cv2.inRange?

A mask = cv2.inRange(hsv, (40, 40, 40), (70, 255, 255))

B mask = cv2.inRange(hsv, {40, 40, 40}, {70, 255, 255})

C mask = cv2.inRange(hsv, np.array([40, 40, 40]), np.array([70, 255, 255]))

D mask = cv2.inRange(hsv, [40, 40, 40], [70, 255, 255])

💡 Hint

cv2.inRange expects numpy arrays for the color bounds.

cv2.inRange requires numpy arrays for lower and upper bounds; lists or tuples may cause errors or unexpected behavior; sets are invalid syntax here.

🚀 Application

expert

Calculate the number of detected color blobs

Given the following code that detects yellow blobs in a drone camera frame, how many blobs will be detected?

Drone Programming

import cv2
import numpy as np

frame = np.zeros((6,6,3), dtype=np.uint8)
frame[1,1] = [0, 255, 255]  # Yellow in BGR
frame[4,4] = [0, 255, 255]  # Yellow in BGR
frame[1,4] = [0, 255, 255]  # Yellow in BGR

hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
lower_yellow = np.array([20, 100, 100])
upper_yellow = np.array([30, 255, 255])

mask = cv2.inRange(hsv, lower_yellow, upper_yellow)

contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

print(len(contours))

A 3

B 1

C 0

D 2

💡 Hint

Each yellow pixel is isolated; contours detect connected regions.

Each yellow pixel is isolated (not connected), so each forms its own contour; total 3 blobs detected.