SE263 Video Analytics
Course Project Initial Report
Presented by M.
Aravind
Krishnan, SERC,
IISc
X. Mei and H. Ling, ICCV’09
AIM
of the course project is to implement and if possible, improve the work done by
X
ue
Mei and
Haibin
Ling in visual tracking, as explained in their paper
Robust Visual
Tracking using
l
1
minimization
.
By ‘
improve
’ it is meant to ‘
accelerate
’ the speed of execution using special
processing hardware called
Graphics Processing Units
.
1.
I will begin by explaining the work done in the paper, and the various mathematical
tools used in achieving the desired results.
1. Bayesian state inference framework, used to predict the affine state of the object.
(Called the particle filter)
2. Sparse representation of the Tracking target.
3. Non

negativity constraints
4.
l
1
minimization
5. Template update
2.
This will be followed by a brief overview of Graphics processing Units, and how they
can be used for general purpose computation.
3.
Finally the parts of the algorithm most suited for being executed in a GPU is
proposed.
OVERVIEW
Templates
•
Sample/collection of possible views of the object, whose linear
combination can be used to represent the tracked object in the
frame.
•
Two types of templates are considered in this paper, Target
templates and Trivial templates.
•
Target templates to deal with various lighting conditions, poses, etc.
•
Trivial templates to deal with occlusions, noise,
bacckground
clutter,
etc.
Templates continued
•
Target templates are densely used to
represent, and hence are less in number.
•
T
rivial templates are sparsely used to
represent, and hence can be large in number.
State of object being tracked
X
t
=
2D deformation parameters
2D translation parameters
If
z
t
is
the
observed
distribution
of
the
state
of
the
object
at
time
t,
then
the
predicted
distribution
of
the
object
x
t
is
given
by
the
recursive
computation
"filtering"
refers
to
determining
the
distribution
of
a
latent
variable
at
a
specific
time,
given
all
observations
up
to
that
time
;
particle
filters
are
so
named
because
they
allow
for
approximate
"filtering"
using
a
set
of
"particles"
(differently

weighted
samples
of
the
distribution
)
.

Wikipedia
l
1
minimization
Non negativity
Optimization
Convex Optimization
–
Interior point method
The
method
uses
the
preconditioned
conjugate
gradients
(PCG
)
algorithm
to
compute
the
search
direction
and
the
run
time
is
determined
by
the
product
of
the
total
number
of
PCG
steps
required
over
all
iterations
and
the
cost
of
a
PCG
step
.
This
process
can
be
accelerated
by
GPUs
.
Algorithm for template update
Review of Algorithm
Frame 1
1.
Manually detect object to be tracked
2.
Initialize Target Templates with random variations of
object
Generate a set of
N
states around current state
X
t
,
with each of
the 6 affine parameters being modeled as an independent
gaussian
variable.
Calculate p(
X
t

Z
1:t
) by determining the Bayesian weights of
the importance
w
i
= p(
z
t
x
t
), in turn determined from the
errors/residuals in projecting the tracked object onto each of
the solutions of
3.
Represent each of the N generated states as a sparse linear
combination of target and trivial templates by solving the
l
1
minimization problem
min
B
c

y

2
2
+
λ
c
1
Update templates if the highest similarity of the templates with
newly tracked object is less than a threshold. Do by replacing
lowest similarity template with the newly tracked object.
1
2
3
4
5
Working of a GPU
•
Consists of a lot ALUs.
Banks of ALUs with shared memory are called
cores.
•
An average CPU consists of
upto
4 SIMD units.
•
A GPU consists of 32

128 SIMD units
•
A tesla C1060 unit available in SERC will be
used to try and speed up the optimization
process, and hence the whole algorithm.
The functionality of
GPUs
–
Data
Parallelism
•
GPUs are extremely good at executing the same
instruction across bulky data.
Eg
. Vector addition, Matrix Vector Multiplication,
BLAS routines, etc.
•
The major bottle

neck of this algorithm is the
convex optimization performed using Interior
point method. It involves some matrix vector
operations over the same matrix and around
N
different vectors. This can be readily and trivially
parallelized, and great speedup can be achieved if
done carefully.
Architecture of GPU
Goals and tasks of project
•
Dividing the minimization algorithm amongst the cores
of the GPU, and figuring out optimal grid configuration.
•
Optimizing to perform the whole task with minimal
data transfer from CPU to GPU and performing the
algorithm in real time using just one kernel invocation,
for a long video.
•
Achieve a frame rate > 30 fps on Tesla C1060.
•
Achieve frame rate of 18 fps or more using ATI mobility
Radeon HD 5650 graphics processor with 1Gb internal
memory available in my laptop. (requires transcription
to
OpenCL
. Under constraints of time)
Thank you
Comments 0
Log in to post a comment