seminar on vision and learning university of california, san diego september 20, 2001
DESCRIPTION
Seminar on Vision and Learning University of California, San Diego September 20, 2001 Learning and Recognizing Human Dynamics in Video Sequences Christoph Bregler Presented by : Anand D. Subramaniam Electrical and Computer Engineering Dept., University of California, San Diego. Outline. - PowerPoint PPT PresentationTRANSCRIPT
Learning and Vision Seminar Anand D. Subramaniam
Seminar on Vision and LearningUniversity of California, San Diego
September 20, 2001
Learning and Recognizing Human Dynamics in Video Sequences
Christoph Bregler
Presented by :Anand D. Subramaniam Electrical and Computer Engineering Dept.,University of California, San Diego
Learning and Vision Seminar Anand D. Subramaniam
Outline• Gait Recognition
• The Layering Approach
• Layer One - Input Image Sequence — Optical Flow
• Layer Two - Coherence Blob Hypothesis — EM Clustering
• Layer Three - Simple Dynamical Categories— Kalman Filters
• Layer Four - Complex Movement Sequences— Hidden Markov Models
• Model training
• Simulation results
Learning and Vision Seminar Anand D. Subramaniam
Gait Recognition
Running
Walking Skipping
Learning and Vision Seminar Anand D. Subramaniam
The Layering Approach
Layer 1
Layer 2
Layer 3
Layer 4
Learning and Vision Seminar Anand D. Subramaniam
Input Image Sequence Layer 1• Feature vector comprises of optical flow, color value and
pixel value.
Optical Flow equation
Affine Motion Model
Affine Warp
0),,(),(),,( yxtIyxvyxtI t
y
x
dysxs
dysxsyxv
2,21,2
2,11,1),(
y
x
d
d
ss
ssS ,
1
1
2,21,2
2,11,1
Learning and Vision Seminar Anand D. Subramaniam
Learning and Vision Seminar Anand D. Subramaniam
Expectation Maximization Algorithm• EM is an iterative algorithm which computes locally optimal
solutions to certain cost functions.
• EM simplifies a complex cost function into a bunch of easily solvable cost functions by introducing a “missing parameter”.
• Missing data is the Indicator Function .y
iS
Learning and Vision Seminar Anand D. Subramaniam
Expectation Maximization Algorithm
• EM iterates between two steps
• E - Step : — Estimate the conditional mean estimate of the missing
parameter given the previous estimate of model parameters and the observations.
• M - Step :— Re-estimate the model parameters given the soft clustering
done by the E - Step.
• EM is numerically stable with the likelihood non-decreasing with every iteration.
• EM converges to a local optima.
• EM has linear convergence.
Learning and Vision Seminar Anand D. Subramaniam
Density Estimation using EM• Gaussian mixture models can be used to model any given
probability density function to arbitrary accuracy by using sufficient number of clusters. ( curve fitting using Gaussian kernels)
• For a given number of clusters, the EM tries to minimize the Kullback-Leibler divergence measure between the arbitrary pdf and the class of Gaussian mixture models with the given number of clusters.
0 200 400 600 800 1000 12000
0.1
0.2
0.3
0.4
0.5
0.6
0.7
Learning and Vision Seminar Anand D. Subramaniam
Coherence Blob Hypotheses Layer 2
k yxkyxk
k yxkk
k yxkk
kkk
k
K
kkkk
yx
tyxyxtIPSC
tyxPyxtSC
yxtSC
tyxyxtIPtyxP
tyxyxtIkyxtSPyxtS
tyxyxtIPtyxPttyxyxtIP
tyxyxtIPtIP
,,,3
,2
,1
0
,
)(,,,,log
)(,log),,(
log,,
)(,,),,()(,
)(,,),,,(),,(,,
)(,,),,()(,)()( ,),,,(
)( ,),,,()(
LikelihoodEquation
MixtureModel
MissingData
SimplifiedCost
Functions
Learning and Vision Seminar Anand D. Subramaniam
EM Initialization
• We need to track the temporal variation of blob parameters in order to initialize the EM for a given frame.
• Kalman filters
• Recursive EM using Conjugate priors
Learning and Vision Seminar Anand D. Subramaniam
Learning and Vision Seminar Anand D. Subramaniam
All Roads Lead From Gauss 1809 “ … since all our measurements and observations are nothing more
than approximations to the truth, the same must be true of all
calculations resting upon them, and the highest aim of all
computations made concerning concrete phenomenon must be to
approximate, as nearly as practicable, to the truth. But this can be
accomplished in no other way than by suitable combination of more
observations than the number absolutely requisite for the determination of
the unknown quantities. This problem can only be properly undertaken
when an approximate knowledge of the orbit has been already attained,
which is afterwards to be corrected so as to satisfy all the observations
in the most accurate manner possible.”
- From Theory of the Motion of the Heavenly Bodies Moving about the Sun in Conic Sections, Gauss, 1809
Learning and Vision Seminar Anand D. Subramaniam
Estimation Basics• Problem statement
• Observation Random variable X (Given)
• Target Random Variable Y (Unknown)
• Joint Probability Density f(x,y) (Given)
• What is the best estimate yopt=g(x) which minimizes the expected mean square error between yopt and y ?
• Answer : Conditional Mean g(x) = E(Y|X=x)
• Estimate g(x) can be potentially nonlinear and unavailable in closed form.
• When X and Y are jointly Gaussian g(x) is linear.
• What is the best linear estimate ylin=Wx which minimizes the mean square error ?
Learning and Vision Seminar Anand D. Subramaniam
Wiener Filter 1940
Wiener-Hopf Solution : W = RYX (Rxx)-1
• Involves Matrix Inversion
• Applies only to stationary processes
• Not amenable for online recursive implementation.
Span(X)
Y
Ylin
Learning and Vision Seminar Anand D. Subramaniam
Kalman Filter
• The estimate can be obtained recursively.
• Can be applied to non-stationary processes.
• If measurement noise and process noise are white and Gaussian, then the filter is “optimal”.
• Minimum variance unbiased estimate
• In the general case, the Kalman filter is the best linear estimator among all linear estimators.
kkkk
kkkk
vyMx
uyAy
1Process Model :
Measurement Model :
STATE SPACE MODEL
Learning and Vision Seminar Anand D. Subramaniam
The Water Tank Problem
tt
ttt
rr
rLL
rdt
dL
1
1 1
Guassian i.i.dmean zero are ,
01
10
11
2,
1,
1
1
kk
kt
tt
k
k
t
t
t
t
vu
vr
LL
u
u
r
L
r
L
Process Model :
Measurement Model :
Learning and Vision Seminar Anand D. Subramaniam
What does a Kalman filter do ?• The Kalman filter propagates the conditional density in time.
-5 -4 -3 -2 -1 0 1 2 3 4 50
0.1
0.2
0.3
0.4
0.5
0.6
0.7
-5 -4 -3 -2 -1 0 1 2 3 4 50
0.1
0.2
0.3
0.4
0.5
0.6
0.7
-5 -4 -3 -2 -1 0 1 2 3 4 50
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8 1xyf 2xyf
21, xxyf
Learning and Vision Seminar Anand D. Subramaniam
How does it do it ?
• The Kalman filter iterates between two steps
• Time Update (Predict)— Project current state and covariance forward to the next time
step, that is, compute the next a priori estimates.
• Measurement Update (Correct)—Update the a priori quantities using noisy measurements, that is,
compute the a posteriori estimates.
• Choose Kk to minimize error covariance
kkkkkk xMxKyy ˆˆˆ
Learning and Vision Seminar Anand D. Subramaniam
Applications
GPS Satellite orbitcomputation
Active noise control
Tracking
Learning and Vision Seminar Anand D. Subramaniam
The Layering Approach
Layer 1
Layer 2
Layer 3
Layer 4
Learning and Vision Seminar Anand D. Subramaniam
Simple Dynamical Categories Layer 3• A sequence of blobs k(t), k(t+1),…, k(t+d) is grouped into
dynamical categories. The group assignment is “soft”.
• The dynamical categories are represented with a set of M second order linear dynamical systems.
• Each category is certain phase during a gait cycle.
• Categories called “movemes” (like “phonemes”).
• Dm(t,k) : Probability that a certain blob k(t) belongs to one of the dynamical categories m.
Q(t) = A1m Q(t-2) + A0m Q(t-1) + Bm w
• Q(t) is the motion estimate of the specific blob k(t), w is the system noise and Cm= Bm .(Bm)T is the system covariance.
• The dynamical systems form states of a Hidden Markov Model.
Learning and Vision Seminar Anand D. Subramaniam
Learning and Vision Seminar Anand D. Subramaniam
The Model
Learning and Vision Seminar Anand D. Subramaniam
Trellis representation
Learning and Vision Seminar Anand D. Subramaniam
HMM in speech
Learning and Vision Seminar Anand D. Subramaniam
HMM model parameters
State Transition Matrix : AObservation state PDF : BNumber of states : NNumber of Observation levels : MInitial probability distribution :
,,,, MNBA
Learning and Vision Seminar Anand D. Subramaniam
Three Basic Problems• Given the observation sequence O = O1
O2…OT, and a model , how do we efficiently compute P(O|), the probability of the observation sequence, given the model ?
• Given the observation sequence O = O1
O2…OT, and the model , how do we choose a corresponding state sequence Q = q1q2…qT, which best “explains” the observations ?
• How do we adjust the model parameters to maximize P(O|) ?
ForwardBackwardAlgorithm
ViterbiAlgorithm
BaumWelch
Algorithm
Learning and Vision Seminar Anand D. Subramaniam
How do they work ? Key ideas
• Both Forward-Backward algorithm and the Viterbi algorithm solve the associated problem by induction (or recursively).
• The induction is a consequence of the Markovity of the model.
• The Baum-Welch is exactly the EM algorithm with a different “missing parameter”.
• The missing parameter is the state a particular observation belongs to.
Learning and Vision Seminar Anand D. Subramaniam
The Layering Approach
Layer 1
Layer 2
Layer 3
Layer 4
Learning and Vision Seminar Anand D. Subramaniam
Complex Movement Sequences Layer 4
• Each dynamical system becomes a state of a Hidden Markov Model.
• Different gaits are modeled using different HMM’s.
• Paper uses 33 sequences of 5 different subjects performing 3 different gait categories.
• Choose that HMM that has the maximum likelihood given the observation.
• Number of correct classified gait cycles in the test set varied from 86% to 93%.
Learning and Vision Seminar Anand D. Subramaniam
References
• EM Algorithm
• A.P. Dempster, N.M. Laird and D.B. Rubin, “Maximum Likelihood from incomplete data via the EM Algorithm”, Journal of the Royal Statistical Society, 39(B),1977.
• Richard A. Redner and Homer F. Walker, “Mixture densities, Maximum likelihood and the EM algorithm”, SIAM Review, vol. 26.,No. 2, April 1984.
• G.J. McLachlan and T. Krishnan, “EM Algorithm and its extensions”, Wiley and Sons, 1997.
• Jeff A. Bilmes, “A Gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and Hidden Markov Models”, available on the net.
Learning and Vision Seminar Anand D. Subramaniam
References
• Kalman Filter
• Anderson, B. D. O. and Moore, J. B. (1979). Optimal Filtering. Prentice-Hall, Englewood Cliffs, NJ.
• H. Sorenson, "Kalman Filtering: Theory and Application," IEEE Press, 1985.
• Peter Maybeck, Stochastic Models, Estimation, and Control, Volume 1, Academic Press. 1979
• Web site : http://www.cs.unc.edu/~welch/kalman/
Learning and Vision Seminar Anand D. Subramaniam
References
• Hidden Markov Models
• Rabiner, “ An introduction to Hidden Markov Models and selected applications in speech recognition”, Proceedings of the IEEE, 1989.
• Rabiner and Juang, “An introduction to Hidden Markov Models”, IEEE ASSP Magazine, 1986.
• M.I. Jordan and C.M. Bishop, “An Introduction to Graphical Models and Machine Learning”, ask Serge.