Optical flow concept in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is optical flow in computer vision?

Optical flow is the pattern of apparent motion of objects, surfaces, and edges in a visual scene caused by the relative motion between an observer and the scene.

beginner

What does optical flow estimate between two video frames?

It estimates the motion vector field that shows how each pixel moves from one frame to the next.

intermediate

Name two common assumptions made when computing optical flow.

1. Brightness constancy: pixel brightness stays the same between frames.<br>2. Small motion: objects move only a little between frames.

beginner

How is optical flow useful in real life?

It helps in video stabilization, object tracking, autonomous driving, and motion detection by understanding how things move in videos.

intermediate

What is the difference between dense and sparse optical flow?

Dense optical flow computes motion for every pixel, while sparse optical flow computes motion only for selected points or features.

What does optical flow primarily measure?

A Color changes in images

B Shape of objects

C Brightness of a single frame

D Motion of pixels between frames

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

Which assumption is essential for computing optical flow?

A Brightness constancy

B Color constancy

C Shape constancy

D Texture constancy

Brightness constancy means pixel brightness stays the same between frames, which is key for optical flow.

Dense optical flow calculates motion for:

A Every pixel

B No pixels

C Random pixels

D Only corners

Dense optical flow finds motion vectors for every pixel in the image.

Optical flow can be used for:

A Adding noise

B Changing image colors

C Video stabilization

D Cropping images

Optical flow helps stabilize videos by understanding motion between frames.

Which is NOT a typical use of optical flow?

A Motion detection

B Image compression

C Object tracking

D Autonomous driving

Image compression is not a typical use of optical flow.

Explain what optical flow is and why it is important in video analysis.

Think about how we see movement in videos and how computers can detect it.

Describe the main assumptions behind optical flow calculation and how they help estimate motion.

Consider what must stay the same or change little for motion to be detected accurately.