A Variational Model for Interactive Shape Prior Segmentation and - - PowerPoint PPT Presentation

a variational model for interactive shape prior
SMART_READER_LITE
LIVE PREVIEW

A Variational Model for Interactive Shape Prior Segmentation and - - PowerPoint PPT Presentation

A Variational Model for Interactive Shape Prior Segmentation and Real-Time Tracking Manuel Werlberger, Thomas Pock, Markus Unger, and Horst Bischof 05/26/2009 Institute for Computer Graphics and Vision Graz University of Technology Motivation


slide-1
SLIDE 1

A Variational Model for Interactive Shape Prior Segmentation and Real-Time Tracking

Manuel Werlberger, Thomas Pock, Markus Unger, and Horst Bischof

05/26/2009

Institute for Computer Graphics and Vision Graz University of Technology

slide-2
SLIDE 2

Motivation

slide-3
SLIDE 3

Motivation

slide-4
SLIDE 4

Even more difficult?

slide-5
SLIDE 5

Outline

Shape Alignment Related Work Shape Prior Segmentation Conclusion and Outlook Applications and Results

slide-6
SLIDE 6

Outline

Shape Alignment Related Work Shape Prior Segmentation Conclusion and Outlook Applications and Results

slide-7
SLIDE 7

Geodesic Active Contour Model

  • Based on Snake Model (Kass et al.)
  • Minimizing weighted length:

|C| … Euclidean length of curve C g … Edge image: g 2 (0,1]

  • Variational formulation – weighted TV:

[Caselles 1997; Bresson 2005; Leung 2005]

slide-8
SLIDE 8

f … observed image u … piecewise smooth approximation ¡ … edges in u

  • Does not pick up textured objects.
  • Only objects featuring a homogeneous region inside the

boundary ¡.

Mumford-Shah Segmentation

[Mumford and Shah 1988]

slide-9
SLIDE 9

Active Contours without Edges

  • Special case of the Mumford-Shah model for Segmentation

proposed by Chan and Vese: f … input image c1, c2 … mean values of the fore- and background intensities

  • Segmentation not bound to image gradients.

[Chan and Vese 2001]

slide-10
SLIDE 10

Diffusion Snakes

  • Mumford-Shah segmentation
  • Incorporate statistical shape knowledge

[Cremers et al. 2002]

slide-11
SLIDE 11

Outline

Shape Alignment Related Work Shape Prior Segmentation Conclusion and Outlook Applications and Results

slide-12
SLIDE 12

Variational Segmentation & Shape Information

  • Reconsider Chan-Vese Segmentation Model:
  • Restated as TV functional:

[Chan et al. 2006]

slide-13
SLIDE 13
  • Data-Fidelity Term: Shape Force

s … Shape representation u … Segmentation result.

Shape Prior Segmentation

  • Signed distance map as shape representation.
  • Regularization: Weighted TV-norm

g … Edges of input image u … Segmentation result.

slide-14
SLIDE 14

Shape Prior Transformation

  • Transformation parameters Á = {t,R,S}

t … Translation R … Rotation S … Scale

  • Parameter ¸ controls influence of the shape force.
slide-15
SLIDE 15

Influence of ¸

¸ = 0.15 ¸ = 0.10 ¸ = 0.05 ¸ = 0.01 ¸ = 0.20

slide-16
SLIDE 16

Solving the Shape Prior Segmentation Model

Updating segmentation u Update transformation parameters Á(t,R,S) Iterate

slide-17
SLIDE 17

Solving the Shape Prior Segmentation Model

  • Dual formulation of weighted TV-norm:
  • Represents a typical saddle-point problem.

[Arrow, Hurwicz 1958; Zhu and Chan 2008]

slide-18
SLIDE 18

Primal-Dual update scheme

  • 1. Primal update:
  • 2. Dual update:
  • 3. Iterate until convergence.

Gradient descend Gradient ascend + reprojection Iterate

slide-19
SLIDE 19

Primal-Dual Gap

slide-20
SLIDE 20

Outline

Shape Alignment Related Work Shape Prior Segmentation Conclusion and Outlook Applications and Results

slide-21
SLIDE 21

Optimizing Shape Transformation

  • Transformation parameters Á = {t,R,S}

t … Translation R … Rotation S … Scale

  • Brute force search:

– simple, but computationally costly. – Performance ok for local optimization. – Not reasonable for a global optimization: The complete subspace Ω has to be sampled.

[Cremers 2008]

slide-22
SLIDE 22

Which position to take?

  • Depending on the Primal energy.

EPrimal = -530 EPrimal = -430 EPrimal = -338

slide-23
SLIDE 23

Outline

Shape Alignment Related Work Shape Prior Segmentation Conclusion and Outlook Applications and Results

slide-24
SLIDE 24

Evaluation on hand-labeled data

Thresholding pure GAC Shape Prior

slide-25
SLIDE 25

User Interaction + Shape Position Optimization

slide-26
SLIDE 26

Low contrast image

Thresholding pure GAC Shape Prior

slide-27
SLIDE 27

Occlusion

slide-28
SLIDE 28

Tracking

slide-29
SLIDE 29

Performance

  • Use benefit of parallelization with CUDA. (Nvidia GTX 280)
  • Shape Prior segmentation (using 200 iterations):
  • Shape Alignment (optimizing Á(t,R,S)):

Image Size Shape Prior Size Performance 416x800 160x160 115 fps 2267x1558 600x600 20 fps Image Size Shape Prior Size Performance 416x800 160x160 25 fps 2267x1558 600x600 5 fps

slide-30
SLIDE 30

Outline

Shape Alignment Related Work Shape Prior Segmentation Conclusion and Outlook Applications and Results

slide-31
SLIDE 31

Conclusion

Segmentation Shape Alignment Tracking

slide-32
SLIDE 32

Outlook

  • Shape space instead of single prior.
  • Use multiple shapes simultaneously.
  • Optimizing elastic instead of rigid shape transformation.
  • Use anisotropic regularization.
  • Extend to 3D.
slide-33
SLIDE 33

Thank you very much for your attention!

Manuel Werlberger, Thomas Pock, Markus Unger, and Horst Bischof