Related Computer Vision Links
Learn Opticalflow Computer Vision Tutorial, validate concepts with Opticalflow Computer Vision MCQ Questions, and prepare interviews through Opticalflow Computer Vision Interview Questions and Answers.
Optical Flow MCQ
Under brightness constancy, pixels appear to move—estimate (u,v) motion fields between frames.
Motion field
(u,v)
Constancy
I_t ≈ I_{t+1}
Aperture
Ambiguity
Smoothness
Regularize
Optical flow basics
Optical flow assigns a 2D displacement to each pixel between frames. Brightness constancy assumes pixel intensity is preserved along motion; combined with spatial smoothness (Horn–Schunck) or local linearization (Lucas–Kanade), it yields estimators. Deep networks now predict dense flow end-to-end (FlowNet, RAFT).
Aperture problem
Along a 1D edge, only the normal component of flow is observable locally—additional constraints resolve ambiguity.
Key ideas
Brightness constancy
I_x u + I_y v + I_t ≈ 0 (first-order).
Lucas–Kanade
Least squares on a patch assuming constant (u,v).
Horn–Schunck
Global smoothness regularizer + data term.
Deep flow
CNNs regress flow from image pairs directly.
From two frames
warp frame2 toward frame1 using estimated flow; minimize photometric error