Title: 3D Computational Vision CSc 83029
13-D Computational VisionCSc 83029
- Optical Flow Motion
- The Factorization Method
2Optical Flow Motion
- Finding the movement of scene objects from
time-varying images. - Motion Field
- Optical Flow
- Computing Optical Flow
3(No Transcript)
4Computing Time-to-Impact t
v
l(t)f L/D(t)
L
l(t)
D0
f
D0-vt
5Computing Time-to-Impact t
v
l(t)f L/D(t)
L
l(t)
D0
f
D0-vt
l(t) / l(t) t Quantities measured from image
sequence.
6Sudden change in viewing position/direction Har
d to compute motion field/optical flow.
7Views from a sequence of spatially close
viewpoints Motion Field/ Optical Flow
8Sub problems of Motion Analysis
- Correspondence.
- Reconstruction.
- Segmentation.
9Motion Field
2-D vector field of velocities of image points,
induced by relative motion between the viewing
camera and the observed points.
Image plane
f
v dt
ri
V dt
p
ro
P
Scene Point Velocity Vdro/dt Image Velocity
v dri/dt
10Motion Field
2-D vector field of velocities of image points,
induced by relative motion between the viewing
camera and the observed points.
Image plane
f
v dt
ri
V dt
p
Perspective projection
ro
P
Velocity of point P as a function of translation
and rotation
Motion field equations
11Motion Field
2-D vector field of velocities of image points,
induced by relative motion between the viewing
camera and the observed points gt SUM of 2
COMPONENTS
12Motion Field
2-D vector field of velocities of image points,
induced by relative motion between the viewing
camera and the observed points gt SUM of 2
COMPONENTS
13Special Case 1 Pure Translation
2-D vector field of velocities of image points,
induced by relative motion between the viewing
camera and the observed points gt SUM of 2
COMPONENTS
14Pure Translation Radial Motion Field
p0(x0,y0)
15Pure Translation Radial Motion Field
- Tz lt 0 FOCUS OF EXPANSION.
- Tz gt 0 FOCUS OF CONTRACTION.
- Tz 0 PARALLEL MOTION FIELD.
- Vanishing point (epipole) p0.
p0(x0,y0)
16Special Case 2 Moving Plane
n
P
Plane moves n,d are functions of time. Motion
field?
17Special Case 2 Moving Plane
n
P
Plane moves n,d are functions of time. Motion
field?
18Special Case 2 Moving Plane
n
P
Plane moves n,d are functions of time. Motion
field?
Motion field quadratic polynomial in (x,y,f) at
any time t. The same motion field can be
produced by 2 different planes undergoing 2
different 3-D motions.
19Motion Parallax
The relative motion field of two instantaneously
coincident points does not depend on the
rotational component of the motion
p0
20The notion of Optical Flow
Optical Flow Estimation of the motion field from
a sequence of images.
21Optical Flow
22Optical Flow
(xudt,yvdt) udx/dt vdy/dt
(x,y)
t
tdt
Image brightness constancy equation E(x,y,t)E(x
udt, yvdt, tdt)
or
23The Aperture Problem
The component of the motion field in
the direction orthogonal to the spatial image
gradient is not constrained by the image
brightness constancy equation.
Aperture problem
Image brightness constancy equation E(x,y,t)E(x
udt, yvdt, tdt)
1 constraint 2 unknowns
24Optical Flow
At each point we know dE/dx dE/dy and dE/dt.
How can we obtain dx/dt and dy/dt?
25Computing Optical Flow
Assumption The motion field is well approximated
by a constant vector field within any small patch
of the image plane.
provides one constraint
Each
Solution is
26Computing Optical Flow
Assumption The motion field is well approximated
by a constant vector field within any small patch
of the image plane.
Q
Minimize
27Computing Optical Flow
Assumption The motion field is well approximated
by a constant vector field within any small patch
of the image plane.
Q
Minimize
gtSolve the linear system
28Computing Optical Flowglobal approach
Schunck and Horn 81
Minimize the error in the image brightness
constancy constraint.
29Computing Optical Flowglobal approach
Schunck and Horn 81
Minimize the error in the image brightness
constancy constraint.
Minimize the deviation from smoothness of the
motion vectors.
30Computing Optical Flowglobal approach
Schunck and Horn 81
Minimize the error in the image brightness
constancy constraint.
Minimize the deviation from smoothness of the
motion vectors.
Find solution by minimizing
where lambda weights the smoothness term.
31Optical Flow
32Optical Flow
33Optical Flow
34Optical Flow
35Optical Flow
If the scene is planar the motion Is described by
Using
Solve for the 8 unknowns a, b, c, d, e, f, g and
h.
36Tracking Rigid Bodies
B
Random Sampling Algorithm Step 1 Find
corners Step 2 Search for correspondence Step 3
Randomly choose small set of matches. Step 4
Estimate F matrix Step 5 Find total number of
matches close to epipolar lines Step 6 Go to
step 3 Step 7 Choose F with largest number of
matches
37(No Transcript)
38Structure and Motion Recovery from Video
1. Use multiple image stream to compute the
information about camera motion and 3D structure
of the scene 2. Tracking image features over time
Tracked Features
Original sequence
From Jana Kosecka
39Structure and Motion Recovery from Video
Computed model 3D coordinates of the feature
points
Original picture
From Jana Kosecka
40Factorization Method
ji
ki
ii
FRAMES i1N
41Factorization Method
Pj
ji
ki
(xij,yij)
ii
FRAMES i1N
World Points j1n
42Factorization Method
Pj
Z
ji
ki
(xij,yij)
Ti
ii
FRAMES i1N
World Points j1n
Y
X
World Reference Frame
43ASSUMPTIONS The camera model is
orthographic! The positions of n image points
have been tracked.
Pj
Z
ji
ki
(xij,yij)
Ti
ii
FRAMES i1N
World Points j1n
Y
X
World Reference Frame
44Measurement Matrix
2N (Frames)
n points per frame
Registered Measurement Matrix
2N (Frames)
n points per frame
45Factorization Method
World Points j1n
Pj
3D Centroid
Z
ji
ki
Ti
ii
FRAMES i1N
Y
X
2D Centroid
World Reference Frame
46Rank Theorem
2N (Frames)
n points per frame
R Rotation Matrix S Shape Matrix
47Rank Theorem
2N (Frames)
n points per frame
R Rotation Matrix S Shape Matrix Rank of
is 3.
48The algorithm
2N (Frames)
n points per frame
Decompose into R and S. Is the decomposition
unique? Translation estimation?
49(No Transcript)