Title: Optical%20Flow
1Optical Flow
Some slides and illustrations from L. Van Gool,
T. Darell, B. Horn, Y. Weiss, P. Anandan, M.
Black, K. Toyama
2last week polar rectification
3Last week polar rectification
4Last week Stereo matching
- Constraints
- epipolar
- ordering
- uniqueness
- disparity limit
- disparity gradient limit
- Trade-off
- Matching cost (data)
- Discontinuities (prior)
(Cox et al. CVGIP96 Koch96 Falkenhagen97
Van Meerbergen,Vergauwen,Pollefeys,VanGool
IJCV02)
5Questions for assignment?
6Tentative class schedule
Aug 26/28 - Introduction
Sep 2/4 Cameras Radiometry
Sep 9/11 Sources Shadows Color
Sep 16/18 Linear filters edges (Isabel hurricane)
Sep 23/25 Pyramids Texture Multi-View Geometry
Sep30/Oct2 Stereo Project proposals
Oct 7/9 Tracking (Welch) Optical flow
Oct 14/16 - -
Oct 21/23 Silhouettes/carving (Fall break)
Oct 28/30 - Structure from motion
Nov 4/6 Project update Camera calibration
Nov 11/13 Segmentation Fitting
Nov 18/20 Prob. segm.fit. Matching templates
Nov 25/27 Matching relations (Thanksgiving)
Dec 2/4 Range data Final project
7Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
8Optical FlowWhere do pixels move to?
9(No Transcript)
10(No Transcript)
11Motion is a basic cue
Even impoverished motion data can elicit a strong
percept
12Applications
- tracking
- structure from motion
- motion segmentation
- stabilization
- compression
- mosaicing
-
13Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
14Definition of optical flow
OPTICAL FLOW apparent motion of
brightness patterns
Ideally, the optical flow is the projection of
the three-dimensional velocity vectors on the
image
?
15Caution required !
Two examples
1. Uniform, rotating sphere ? O.F. 0
2. No motion, but changing lighting
? O.F. ? 0
?
16Caution required !
17Mathematical formulation
I (x,y,t) brightness at (x,y) at time t
Brightness constancy assumption
Optical flow constraint equation
?
18Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
19The aperture problem
1 equation in 2 unknowns
?
20The aperture problem
0
21(No Transcript)
22The aperture problem
23Remarks
24Apparently an aperture problem
?
25What is Optic Flow, anyway?
- Estimate of observed projected motion field
- Not always well defined!
- Compare
- Motion Field (or Scene Flow)
- projection of 3-D motion field
- Normal Flow
- observed tangent motion
- Optic Flow
- apparent motion of the brightness pattern
- (hopefully equal to motion field)
- Consider Barber pole illusion
26(No Transcript)
27Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
28Horn Schunck algorithm
Additional smoothness constraint
besides OF constraint equation term
minimize es?ec
?
29The calculus of variations
look for functions that extremize functionals
?
30Calculus of variations
Suppose
1. f(x) is a solution
2. ? (x) is a test function with ? (x1) 0
and ? (x2) 0
for the optimum
?
31Calculus of variations
regardless of ?(x), then
Euler-Lagrange equation
?
32Calculus of variations
Generalizations
?
33Calculus of variations
0
?
34Calculus of variations
is the Euler-Lagrange equation
?
35Horn Schunck
The Euler-Lagrange equations
In our case ,
?
36Horn Schunck
Remarks
1. Coupled PDEs solved using iterative
methods and finite differences
2. More than two frames allow a better
estimation of It
3. Information spreads from corner-type
patterns
?
37?
38Horn Schunck, remarks
1. Errors at boundaries
2. Example of regularisation (selection
principle for the solution of illposed
problems)
?
39Results of an enhanced system
40Structure from motion with OF
41Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
42 43(No Transcript)
44(No Transcript)
45(No Transcript)
46(No Transcript)
47Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
48(No Transcript)
49(No Transcript)
50(No Transcript)
51Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
52(No Transcript)
53(No Transcript)
54(No Transcript)
55(No Transcript)
56(No Transcript)
57(No Transcript)
58(No Transcript)
59(No Transcript)
60(No Transcript)
61(No Transcript)
62(No Transcript)
63(No Transcript)
64(No Transcript)
65(No Transcript)
66(No Transcript)
67(No Transcript)
68(No Transcript)
69(No Transcript)
70(No Transcript)
71(No Transcript)
72(No Transcript)
73(No Transcript)
74(No Transcript)
75(No Transcript)
76(No Transcript)
77(No Transcript)
78(No Transcript)
79(No Transcript)
80(No Transcript)
81Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
82(No Transcript)
83(No Transcript)
84(No Transcript)
85Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
86(No Transcript)
87(No Transcript)
88(No Transcript)
89(No Transcript)
90(No Transcript)
91Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
92(No Transcript)
93(No Transcript)
94(No Transcript)
95(No Transcript)
96(No Transcript)
97(No Transcript)
98Optical Flow
- Brightness Constancy
- The Aperture problem
- Regularization
- Lucas-Kanade
- Coarse-to-fine
- Parametric motion models
- Direct depth
- SSD tracking
- Robust flow
- Bayesian flow
99(No Transcript)
100Rhombus Displays
http//www.cs.huji.ac.il/yweiss/Rhombus/
101(No Transcript)
102(No Transcript)
103(No Transcript)
104(No Transcript)
105(No Transcript)
106(No Transcript)