Optical flow concept in Computer Vision - Model Pipeline Trace

Model Pipeline - Optical flow concept

Optical flow estimates how pixels move between two video frames. It helps computers understand motion by tracking changes in pixel positions over time.

Data Flow - 5 Stages

1Input frames

2 frames x 480 rows x 640 columns x 3 channels→Load two consecutive video frames→2 frames x 480 rows x 640 columns x 3 channels

Frame 1 and Frame 2 from a video showing a moving car

↓

2Grayscale conversion

2 frames x 480 rows x 640 columns x 3 channels→Convert RGB frames to grayscale to simplify processing→2 frames x 480 rows x 640 columns x 1 channel

Grayscale images highlighting brightness changes

↓

3Compute pixel differences

2 frames x 480 rows x 640 columns x 1 channel→Calculate brightness changes between frames→1 frame x 480 rows x 640 columns x 1 channel

Difference image showing moving edges

↓

4Estimate flow vectors

1 frame x 480 rows x 640 columns x 1 channel→Calculate motion vectors (horizontal and vertical) for each pixel→1 frame x 480 rows x 640 columns x 2 channels

Flow field showing direction and speed of pixel movement

↓

5Post-processing

1 frame x 480 rows x 640 columns x 2 channels→Smooth and filter flow vectors to reduce noise→1 frame x 480 rows x 640 columns x 2 channels

Cleaned flow vectors ready for visualization or analysis

Training Trace - Epoch by Epoch

Loss
0.5 |****
0.4 |*** 
0.3 |**  
0.2 |*   
0.1 |    
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.45	0.60	Initial training with high error and moderate accuracy
2	0.32	0.75	Loss decreased, accuracy improved as model learns motion patterns
3	0.25	0.82	Better flow estimation, smoother vector predictions
4	0.20	0.87	Model converging with consistent improvement
5	0.17	0.90	Final epoch shows low loss and high accuracy

Prediction Trace - 4 Layers

Layer 1: Input frames

Layer 2: Compute pixel differences

Layer 3: Estimate flow vectors

Layer 4: Post-processing

Model Quiz - 3 Questions

What does the optical flow algorithm primarily estimate?

A The brightness of a single pixel

B The movement of pixels between two frames

C The color changes in a single image

D The shape of objects in one frame

Key Insight

Optical flow helps machines understand motion by tracking pixel changes between frames. Converting to grayscale simplifies calculations, and training improves the model's ability to predict smooth and accurate motion vectors.

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