Date post: | 15-Jan-2016 |
Category: |
Documents |
Upload: | zoe-watson |
View: | 214 times |
Download: | 0 times |
Slide 1 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Shape Recovery from Medical Image Data Using Extended
Superquadrics
Talib Bhabhrawala
Advisor : Dr. Venkat KroviDepartment of Mechanical and Aerospace EngineeringState University of New York at Buffalo
Master of Science Thesis DefenseDecember 14th, 2004
Slide 2 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Introduction Background Methodology Results Conclusion
• Introduction • Background • Methodology Development • Case Studies• Interfaces• Conclusion & Future Work
Overview
Slide 3 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Explos ion inavailability and
form of 3Ddata.
Ubiquitous availability of computation and communication infrastructure
Introduction Superquadrics Methodology Results Conclusion
Introduction
Create, manipulate & distribute such data.
Slide 4 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Model Based Reconstruction– Building geometric shape models from raw input data – Data reduction, Analysis, Manipulation, Storage
Computer Vision & Animation Life sciencesEngineering
Introduction Superquadrics Methodology Results Conclusion
Introduction
Point Cloud Data is adequate for Visualization
Application Areas
– Models & Methods are defined by the final application– Visualization – Surface Geometry– Dynamic & Finite Element Analysis – Volumetric Information
Slide 5 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Desired Characteristics
Low Order Models– Computational ease.– Fitting, Visualizing & Analysis
Parametric Models - Intuitive and Easy to use
- Meaningful and repeatable
- Great Success in Engineering
Models whose nature is approximation
- Tractability for infinite dimensional data
Slide 6 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
How can we leverage the same framework to additionally parametrically explore multi-resolution hierarchical indexing, storage, searching, reconstruction and retrieval?
Introduction Superquadrics Methodology Results Conclusion
Research Issues
Which kind of a parametric approximation framework would be most suitable for rapid, easy, accurate and computationally inexpensive shape modeling and conversion to volumetric solid model from a dense sampling of the surface?
Slide 7 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
- flexible family of parametric objects - using low order parameterization, variety of shapes maybe obtained - simple mathematical representation- good explicit and implicit form
Superquadrics (SQ)
Introduction Superquadrics Methodology Results Conclusion
powerful & compact shape representation
Slide 8 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
cosm( ) = , / 2 / 2
sin
cosh( ) = ,
sin
A 3D surface can be obtained by the spherical product of two 2D curves.
When a half circle in a plane orthogonal to the (x, y) plane.
is crossed with the full circle in (x, y) plane
/2 /2cos cos
( , ) ( ) ( ) cos sin ,
sin
x
r m h y
z
Introduction Superquadrics Methodology Results Conclusion
Spherical Product
Slide 9 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
A superellipse is a closed curve defined by
Introduction Superquadrics Methodology Results Conclusion
Superellipses
1x y
a b
Slide 10 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Superellipsoids are obtained from superellipses
a1, a2, a3 - scaling factors ε1 , ε 2 - relative roundness & squareness.
1 2
1 1
2 2
3
( , ) ( ) ( )
cos cos2 2cos sin ,
sin
r s s
a a
a a
a
Introduction Superquadrics Methodology Results Conclusion
Superquadrics
Slide 11 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
10.3 3
20.3 3
Introduction Superquadrics Methodology Results Conclusion
Superquadrics
Slide 12 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Valuable single implicit function.
• The object is continuous everywhere.
• Point membership classification can be done
• Inside–outside function.
1
22/2 / 2 /
1 2 3
1x y z
a a a
Introduction Superquadrics Methodology Results Conclusion
Implicit Representation
Slide 13 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Advantages
– can model a diverse set of objects– compact representations– controllability and intuitive meaning– can be recovered from 3D information robustly
Introduction Superquadrics Methodology Results Conclusion
Limitations– Basic representation can only model symmetrical shapes
SQ Discussion
Slide 14 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
• Superquadric’s applications
– Computer environments (Montiel, 1997; Pentland, 2000)– Graphics & vision (Chella, 2000; Jacklic, 2000)
• Local and Global Deformations
– Nonlinear deformable models (Solina & Bajcsy, 1991)– Simulating equations of motion (Terzopoulos, 1993)
• Increasing the DOF
– Segmentation (e.g. Löffelman and Gröller, 1994)– blending multiple models (DeCarlo & Metaxas, 1998)– free form deformations (Bardinet et al., 1994)
Introduction Superquadrics Methodology Results Conclusion
Literature
Slide 15 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
To represent more complex shapes there is a trade off between
- degrees of freedom & expressive power
Zhou and Kambhamettu (2001) first examined
- exponents need not be fixed- possibly be spatially varying functions- extended superquadrics
Introduction Superquadrics Methodology Results Conclusion
Literature
Slide 16 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Analogous to a SQ it is defined by
• & are the latitude & longitude angles • Exponents are now functions of these angles.
( ) ( )1 1
( ) ( )
2 2
( )
3
cos cos
2 2cos sin ,
sin
f f
f f
f
a a
a a
a
Introduction Superquadrics Methodology Results Conclusion
Extended Superquadrics (ESQ)
Slide 17 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Measure the difference between a modeled shape and the given data set
2 2
2 2 2
1 2 1
atan 2
atan 2
1
f f f
f
f
z
x y
y
x
x y x
a a a
where
Introduction Superquadrics Methodology Results Conclusion
Inside-Outside Function
Slide 18 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
The shape of the exponent functions have to be controllable
We introduce a spline as the exponent function.
This interpolated curve acts like a look up table for the algorithm
-2 -1.5 -1 -0.5 0 0.5 1 1.5 20.5
0.6
0.7
0.8
0.9
1
1.1
1.2
( )f
Introduction Superquadrics Methodology Results Conclusion
Exponent Functions
Slide 19 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Introduction Superquadrics Methodology Results Conclusion
Intuitive Example
Slide 20 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Problem Statement
• Recovering a superquadric model from a set of 3D points– Superquadric model
– Vector of superquadric parameters – Input Points
– Minimize
• Least square distance between SQ surface & data points
( )f P
P
3:g
, ,( ) 1,..,Ti i i iX x y z i N
1
( ( )) ( ( )) ( ( ))N
Ti i i
i
g X f P X f P X f P
Slide 21 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
3
s
s 1, 2, , 1 2
s
( , ε ,ε )
x
y F a a a
z
SQ in a local coordinate system
1
s
s
s
x x
y T y
z z
SQ in the general position Transform the points to the object coordinated system
Introduction Superquadrics Methodology Results Conclusion
Five parameters which
define the size & shape
Initial Model Definition
Slide 22 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
31 2 , , 1 1 p 1 1 1 p( , , , , , , ( )..... ( ), ( )..... ( ))s
s x y z
s
x
y F a a a p p p f f f f
z
,
Applying the Inverse Transform & using Euler angles
31, 2, , 1 2 , ,( , , , , )s
s x y z
s
x
y F a a a p p p
z
, Additional six parameters which
define the position and orientation
Case of Extended Superquadrics
Exponent is a spline interpolating ‘p’ control points increases the total number of parameters by 2(p-1).
Number of parameters are now 9+2(p-1).
Introduction Superquadrics Methodology Results Conclusion
Initial Model Definition
Slide 23 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Farthest range point along each coordinate axis which gives an estimate of a1, a2 & a3
Object recognition and pose estimation
xx xy xz
yx yy yz
zx zy zz
I I I
M I I I
I I I
Obtain the rotation matrix and eigen vectors.
Orient axes along minimal & maximal moment of inertia
2 2
1
2 2
1
2
1
1
1
1
1( ) ( )
1( ) ( )
1( ) ( )
1( )( )
1( )( )
1( )( )
N
xx i ii
N
yy i ii
N
zz i ii
N
xy i ii
N
xz i ii
N
xz i ii
I y y z zN
I x x z zN
I y y x xN
I y y x xN
I z z x xN
I z z x xN
Introduction Superquadrics Methodology Results Conclusion
Moment Based Estimation
Slide 24 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
The error-of-fit function is define using the inside–outside function
2N data
i i ii=1EOF = 1- f x ,y , z
EOF varies quickly where the exponents are largeand slowly where exponents are small
2N data
i i ii=1EOF2 = 1- f x ,y ,
fz
Introduction Superquadrics Methodology Results Conclusion
Added to remove the bias
Error of Fit Function
Slide 25 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
2N data
1 2 3 i i ii=1EOF3 = a a a 1- f x ,y ,
fz
Ambiguity in Description– A set of exponent functions in conjunction with scaling
parameters can generate the same shape as another set
To solve the ambiguity, the minimum volume constraint is added
Introduction Superquadrics Methodology Results Conclusion
Error of Fit Function
Metric to be minimized for the “fitting”
Slide 26 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Minimize
where
Variables
tan 2 0
tan 2 0
1, 2, 3 0
f a
f a
a a a
2N data
1 2 3 i i ii=1F = a a a 1- f x ,y ,
fz
Introduction Superquadrics Methodology Results Conclusion
Optimization Problem
3
11, 2, 1 1 p 1 1 1 p[ , ( )..... ( ), ( )..... ( )]P a a a f f f f
Slide 27 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Guided random T echniques
EvolutionaryA lgorithms
GeneticA lgorithms
•The conventional method used is the Levenberg-Marquardt algorithm• Fast and accurate • Problems of local minima• Heavily dependent on initial estimates
Search T echniques
Calculus -B ased Guided random Enumerative
I ndirec tM ethods
Direc t M ethods
S imulatedAnnealing
EvolutionaryA lgorithms
DynamicP rogramming
Calculus - B ased
Introduction Superquadrics Methodology Results Conclusion
Choice of Optimization Method
Slide 28 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
• Inspired by Biological Evolution and its principles
• The evolution of life on earth can be
regarded as one long optimization process though it’s up to debate if this process has reached a optimum yet…
Introduction Superquadrics Methodology Results Conclusion
Genetic Algorithms
Slide 29 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Salient Features
• Requires little insight into the problem
• Ideal if a problem is non convex or has a very large multimodal solution space
• Heuristics Based, does not require derivatives
• Provides with “Good” Solutions
• Ideal exploratory tool to examine new approaches
Genetic Algorithms
Slide 30 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Genetic Algorithms
Components of a GA
Population size: 20 – 100
Crossovers: 50-60%
Mutations: < 5%
Generations: 20 – 2000
- Encoding technique (double vector, binary)- Object function (environment)- Genetic operators (selection, mutation, crossover)
“Typical” tuning parameters
initialize population;evaluate population;while TerminationCriteriaNotSatisfied{
select parents for reproduction;perform crossover & mutation;evaluate population;
}
Slide 31 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Introduction Superquadrics Methodology Results Conclusion
T r an s f o r m toO b jec t C o o r d in a te
S y s tem
G o o d F it?
O b ta in P o in tC lo u d D ata
S tar tM o m en t Bas ed
E s tim atio n o f s izean d O r ien ta tio n
S et N u m b er o fC o n tr o l P o in ts to
2
S et G AP ar am eter s
M in im ize E O F 3T r an s f o r m to
O b jec t C o o r d in a teS y s tem
D is p lay th eF itted ES Q
Ad d a C o n tr o lP o in t
Ye s
N o
Shape Recovery Algorithm
Slide 32 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Introduction Superquadrics Methodology Results Conclusion
2D Case Study
Slide 33 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Introduction Superquadrics Methodology Results Conclusion
3D Case Study
Slide 34 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
• Difficult to fit a complex model using a single extended superquadric
• Segment an object into primitives
2N data
i ii=1EOF2 = 1- f x ,y
f
Maximum Error2
M data
i=1
( )EOF
M
-25 -20 -15 -10 -5 0 5 10 15 20 25
-10
-5
0
5
10
15
20
25
Partitioning Line
dminimize
-20 -15 -10 -5 0 5 10 15 20 25-20
-15
-10
-5
0
5
10
15
20
25
Two Superquadrics to approximate the data
EOF1= 0.575
EOF2= 0.326
Introduction Superquadrics Methodology Results Conclusion
Iterative Segmentation & Recovery
Slide 35 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Introduction Superquadrics Methodology Results Conclusion
Volume Segmentation Using ESQ
• 2D contours are obtained and are stacked • Topological Accuracy is high• Loses Compact representation• Laborious process & model has inconsistencies • Requires a post-processing step
Slide 36 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Introduction Superquadrics Methodology Results Conclusion
PC Based Interface
Slide 37 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
Java EnabledBrowser On Remote
Computer
Web Server
Matlab
Internet TCP/IP
Computational /VisualizationCapabilities
Introduction Superquadrics Methodology Results Conclusion
Web Based Interface
Slide 38 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
• Flexible enough for an asymmetric object that deform smoothly on spheres
• Variable coefficients of the continuous exponents offer a compact parameter space and broad coverage
• The descriptive parameterization is directly incorporated into the model formulation
Introduction Superquadrics Methodology Results Conclusion
Conclusion
Slide 39 of 40 Automation, Robotics and Mechatronics Lab, SUNY at Buffalo
• A more intuitive and robust segmentation scheme
• Techniques for creating “tailored” models from such simple general purpose models
• More intelligent precursor steps to improve convergence speed of the algorithm
• Systematic way to extract and store characteristic signatures of shape
Introduction Superquadrics Methodology Results Conclusion
Future Work