lecture 4: video applications · 2016-07-27 · lecture 4: video applications topological time...
TRANSCRIPT
Lecture 4: Video Applications
Topological Time Series Analysis - Theory And Practice
Jose Perea, Michigan State University. Chris Tralie, Duke University
7/21/2016
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Table of Contents
I Sliding window video definition / examples
B Sliding window video formalism
B Natural video dynamics/geometry
B Memory efficiency / preprocessing
B Interactive Example
B KTH Dataset
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Sliding Window Videos
Y[n]=
X[n]
.
.
.
Time
M
X[n+1]
X[n+2]
X[n+M-1]
X[n]
X[n+M-1]
http://www.ctralie.com/Research/SlidingWindowVideo-SOCG2016/
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Examples
Jumping jacks, heartbeat animation, my neck
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Table of Contents
B Sliding window video definition / examples
I Sliding window video formalism
B Natural video dynamics/geometry
B Memory efficiency / preprocessing
B Interactive Example
B KTH Dataset
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Table of Contents
B Sliding window video definition / examples
B Sliding window video formalism
I Natural video dynamics/geometry
B Memory efficiency / preprocessing
B Interactive Example
B KTH Dataset
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Pure Cosine Composition Model
On the board
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Oscillating Line Segment
0 20 40 60 80 100120140Pixel Index i
0
50
100
150
200
Tim
e t
Oscillating Line Segment Raw Embedding 2D PCA T-length Embedding 2D PCA
B Good Toy Example for Natural VideoB 2 questions
1. Why is it path-like without embedding?2. Why is it curved?
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Oscillating Line Segment
0 20 40 60 80 100120140Pixel Index i
0
50
100
150
200
Tim
e t
Oscillating Line Segment Raw Embedding 2D PCA T-length Embedding 2D PCA
B Good Toy Example for Natural VideoB 2 questions
1. Why is it path-like without embedding?
2. Why is it curved?
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Oscillating Line Segment
0 20 40 60 80 100120140Pixel Index i
0
50
100
150
200
Tim
e t
Oscillating Line Segment Raw Embedding 2D PCA T-length Embedding 2D PCA
B Good Toy Example for Natural VideoB 2 questions
1. Why is it path-like without embedding?2. Why is it curved?
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Jumping Jacks Example
Show PCA Videos
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Distance Matrix Interpretation
Oscillating Bar
Raw Embedding 2D PCA T-length Embedding 2D PCA
0 50 100 150Frame Number
0
50
100
150
Fram
e N
um
ber
0 20 40 60 80 100 120 140Frame Number
0
20
40
60
80
100
120
140
Fram
e N
um
ber
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Distance Matrix Interpretation
Convolving along diagonals (show video)
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Distance Matrix Interpretation
Jumping Jacks
0 2 4 6 8RHSV Number
0
20
40
60
80
100
Fram
e Nu
mbe
rRight Hand Singular Vectors 2D PCA
0 20 40 60 80 100Frame Number
0
20
40
60
80
100
Fram
e Nu
mbe
r
Self-Similarity Matrix
0 2 4 6 8RHSV Number
0
10
20
30
40
50
60
70
Fram
e Nu
mbe
r
Right Hand Singular Vectors 2D PCA
0 10 20 30 40 50 60 70Frame Number
0
10
20
30
40
50
60
70
Fram
e Nu
mbe
r
Self-Similarity Matrix
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Oscillating Line Segment
Why is it curved?B Eulerian pixel view
0 20 40 60 80 100 120 140 160Pixel Index i
0
50
100
150
200
250
Tim
e t
Oscillating Line Segment
0 50 100 150 2002.0
1.5
1.0
0.5
0.0
0.5
1.0
1.5
2.0Pixel Index 40
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Jumping Jacks Video Eulerian View
Show video
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Principal Component Videos
Show videos for heartbeat and jumping jacks
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Table of Contents
B Sliding window video definition / examples
B Sliding window video formalism
B Natural video dynamics/geometry
I Memory efficiency / preprocessing
B Interactive Example
B KTH Dataset
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Naive Embedding
Naive video stacking blows up in memory!
B E.g. 400x400 video of length 300 frames, delay of 30frames
Solution?
B Do SVD
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Naive Embedding
Naive video stacking blows up in memory!
B E.g. 400x400 video of length 300 frames, delay of 30frames
Solution?
B Do SVD
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Naive Embedding
Naive video stacking blows up in memory!
B E.g. 400x400 video of length 300 frames, delay of 30frames
Solution?
B Do SVD
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Naive Embedding
Naive video stacking blows up in memory!
B E.g. 400x400 video of length 300 frames, delay of 30frames
Solution?
B Do SVD
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
What About Drift?
e.g. X (t) = (cos(t), sin(t), t)Show video
B Take smoothed time derivative of each pixel
g(t) = te−t2/(2σ2)
B Can be interpreted as a bandpass filter
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
What About Drift?
e.g. X (t) = (cos(t), sin(t), t)Show video
B Take smoothed time derivative of each pixel
g(t) = te−t2/(2σ2)
B Can be interpreted as a bandpass filter
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
What About Drift?
e.g. X (t) = (cos(t), sin(t), t)Show video
B Take smoothed time derivative of each pixel
g(t) = te−t2/(2σ2)
B Can be interpreted as a bandpass filter
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
1D Drift Example
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Table of Contents
B Sliding window video definition / examples
B Sliding window video formalism
B Natural video dynamics/geometry
B Memory efficiency / preprocessing
I Interactive Example
B KTH Dataset
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
Table of Contents
B Sliding window video definition / examples
B Sliding window video formalism
B Natural video dynamics/geometry
B Memory efficiency / preprocessing
B Interactive Example
I KTH Dataset
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
KTH Dataset
http://www.nada.kth.se/cvap/actions/
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
KTH Dataset
B We are not doing activity recognition!!Castrodad, Alexey, and Guillermo Sapiro. “Sparse modeling of human actionsfrom motion imagery.” International journal of computer vision 100.1 (2012):1-15.
B Instead, we will be ranking periodicity
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
KTH Dataset: Experiment 1
Window length vs persistence
B Keep dimension fixed. For window length W , τ = d/WB Keep number of points fixed. dT = (N − dτ)/NB Take blocks of 160 frames
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
KTH Dataset: Experiment 1
Window length vs persistence
B Keep dimension fixed. For window length W , τ = d/W
B Keep number of points fixed. dT = (N − dτ)/NB Take blocks of 160 frames
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
KTH Dataset: Experiment 1
Window length vs persistence
B Keep dimension fixed. For window length W , τ = d/WB Keep number of points fixed. dT = (N − dτ)/N
B Take blocks of 160 frames
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
KTH Dataset: Experiment 1
Window length vs persistence
B Keep dimension fixed. For window length W , τ = d/WB Keep number of points fixed. dT = (N − dτ)/NB Take blocks of 160 frames
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
KTH Dataset: Experiment 2 (Interactive)
Rank 4 videos as a class
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications
KTH Dataset: Experiment 3 (Interactive)
Rank all videos for a particular person
Topological Time Series Analysis - Theory And Practice Lecture 4: Video Applications