Optical flow concept in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What does optical flow represent in video analysis?

In simple terms, what does optical flow describe when analyzing a video sequence?

A The color changes of objects over time

B The pattern of apparent motion of objects between consecutive frames

C The brightness level of each pixel in a single frame

D The audio signal associated with the video

💡 Hint

Think about how objects move from one frame to the next in a video.

Optical flow captures how pixels move between frames, showing motion patterns.

❓ Predict Output

intermediate

Output of Optical Flow Calculation Code

What is the shape of the output array from the following optical flow calculation using OpenCV's calcOpticalFlowFarneback function?

Computer Vision

import cv2
import numpy as np
prev_frame = np.zeros((100, 100), dtype=np.uint8)
next_frame = np.zeros((100, 100), dtype=np.uint8)
flow = cv2.calcOpticalFlowFarneback(prev_frame, next_frame, None, 0.5, 3, 15, 3, 5, 1.2, 0)
output_shape = flow.shape

A (100, 100, 2)

B (100, 100)

C (2, 100, 100)

D (100, 2)

💡 Hint

Optical flow returns a vector for each pixel indicating motion in x and y directions.

The output is a 3D array with height and width matching the input frames, and 2 channels for horizontal and vertical flow components.

❓ Model Choice

advanced

Choosing a Model for Dense Optical Flow Estimation

Which model architecture is best suited for estimating dense optical flow between two images?

A A convolutional neural network designed to output a 2-channel flow field for each pixel

B A simple feedforward network with a single output neuron

C A recurrent neural network designed for text generation

D A clustering algorithm like K-means

💡 Hint

Dense optical flow requires per-pixel motion vectors.

CNNs can learn spatial features and output a flow vector per pixel, making them ideal for dense optical flow.

❓ Hyperparameter

advanced

Effect of Pyramid Scale Parameter in Optical Flow Calculation

In the Farneback optical flow algorithm, what is the effect of increasing the pyramid scale parameter (pyr_scale)?

A It decreases the number of pyramid levels, reducing accuracy

B It controls the threshold for motion vector magnitude

C It changes the color space of the input images

D It increases the resolution of the image pyramid, allowing finer motion detection but increasing computation time

💡 Hint

Think about how image pyramids help detect motion at different scales.

A larger pyr_scale means the pyramid images are closer in size, increasing resolution and detail but requiring more computation.

❓ Metrics

expert

Evaluating Optical Flow Accuracy with Endpoint Error

Given ground truth flow vectors and predicted flow vectors, how is the average endpoint error (EPE) calculated?

A By measuring the correlation coefficient between predicted and true flow magnitudes

B By counting the number of pixels where predicted flow equals ground truth exactly

C By computing the average Euclidean distance between predicted and true flow vectors over all pixels

D By calculating the mean squared error of pixel intensities

💡 Hint

Endpoint error measures how far off the predicted motion vectors are from the true ones.

EPE is the average length of the vector difference between predicted and ground truth flow vectors, showing average prediction error.

Practice

1. What does optical flow represent in computer vision?

easy

A. The pattern of apparent motion of objects between two images

B. The color distribution in a single image

C. The brightness level of an image

D. The shape of objects detected in an image

Solution

1. Step 1: Understand the meaning of optical flow

   Optical flow describes how pixels move from one image frame to the next, showing motion.

2. Step 2: Compare options to definition

   Only The pattern of apparent motion of objects between two images correctly describes motion between images, while others describe unrelated image properties.

3. Final Answer:

   The pattern of apparent motion of objects between two images -> Option A

4. Quick Check:

   Optical flow = motion pattern [OK]

Hint: Optical flow = pixel motion between frames [OK]

Common Mistakes:

• Confusing optical flow with color or brightness
• Thinking optical flow detects object shapes
• Assuming optical flow works on single images

2. Which OpenCV function is commonly used to compute dense optical flow using the Farneback method?

easy

A. cv2.calcOpticalFlowPyrLK()

B. cv2.findContours()

C. cv2.threshold()

D. cv2.calcOpticalFlowFarneback()

Solution

1. Step 1: Recall OpenCV functions for optical flow

   Farneback method is implemented in OpenCV as cv2.calcOpticalFlowFarneback().

2. Step 2: Eliminate unrelated functions

   Other options relate to tracking points, contours, or thresholding, not Farneback optical flow.

3. Final Answer:

   cv2.calcOpticalFlowFarneback() -> Option D

4. Quick Check:

   Farneback method = calcOpticalFlowFarneback [OK]

Hint: Farneback method uses cv2.calcOpticalFlowFarneback() [OK]

Common Mistakes:

• Confusing Farneback with Lucas-Kanade method
• Choosing functions unrelated to optical flow
• Mixing up function names with similar prefixes

3. Given the following Python code using OpenCV, what is the shape of the output variable flow?

import cv2
prev_img = cv2.imread('frame1.png', 0)
next_img = cv2.imread('frame2.png', 0)
flow = cv2.calcOpticalFlowFarneback(prev_img, next_img, None, 0.5, 3, 15, 3, 5, 1.2, 0)

medium

A. A 3D array with shape (height, width, 2)

B. A 2D array with shape (height, width)

C. A 1D array with length equal to number of pixels

D. A scalar value representing average flow

Solution

1. Step 1: Understand output of Farneback optical flow

   The function returns a 3D array where each pixel has a 2D flow vector (x and y components).

2. Step 2: Match output shape to options

   This means the output shape is (height, width, 2), representing flow vectors per pixel.

3. Final Answer:

   A 3D array with shape (height, width, 2) -> Option A

4. Quick Check:

   Flow shape = (H, W, 2) [OK]

Hint: Optical flow output has two channels for x and y motion [OK]

Common Mistakes:

• Assuming output is 2D grayscale image
• Thinking output is a single scalar
• Confusing flow vector dimensions

4. You wrote this code to compute optical flow but get an error:

flow = cv2.calcOpticalFlowFarneback(prev_img, next_img, 0, 0.5, 3, 15, 3, 5, 1.2, 0)

What is the likely cause of the error?

medium

A. The window size parameter is missing

B. The images must be color, not grayscale

C. The third argument must be None, not 0

D. The pyramid scale parameter is too high

Solution

1. Step 1: Check the third argument of calcOpticalFlowFarneback

   The third argument is the output flow array or None to create it internally; passing 0 causes an error.

2. Step 2: Verify correct usage

   Passing None lets OpenCV allocate the output; 0 is invalid and causes a type error.

3. Final Answer:

   The third argument must be None, not 0 -> Option C

4. Quick Check:

   Third argument = None [OK]

Hint: Use None as third argument to allocate flow output [OK]

Common Mistakes:

• Passing 0 instead of None for output flow
• Using color images instead of grayscale
• Misunderstanding parameter order

5. You want to track a fast-moving object in a video using optical flow. Which approach helps improve accuracy?

hard

A. Use a larger window size and fewer pyramid levels

B. Use a smaller window size and increase pyramid levels

C. Convert images to color before computing flow

D. Apply thresholding before computing flow

Solution

1. Step 1: Understand parameters affecting optical flow accuracy

   Smaller window size captures finer motion details; more pyramid levels help track fast motion at multiple scales.

2. Step 2: Evaluate options for fast-moving object tracking

   Use a smaller window size and increase pyramid levels correctly suggests smaller window and more pyramid levels to improve tracking accuracy.

3. Final Answer:

   Use a smaller window size and increase pyramid levels -> Option B

4. Quick Check:

   Smaller window + more pyramids = better fast motion tracking [OK]

Hint: Smaller window + more pyramids track fast motion better [OK]

Common Mistakes:

• Using large windows that blur fast motion
• Ignoring pyramid levels for scale changes
• Preprocessing images incorrectly