Download - Shape Correspondence through Landmark Sliding

Transcript
Page 1: Shape Correspondence through Landmark Sliding

Anup Kedia

Shape Correspondence through Landmark Sliding

Anup Kedia

Page 2: Shape Correspondence through Landmark Sliding

Introduction

• Shape• Landmarks

Page 3: Shape Correspondence through Landmark Sliding

Contd..

• Landmark Sliding• Shape Correspondence

• Result

Page 4: Shape Correspondence through Landmark Sliding

Need

• Statistical Shape Analysis

• Accuracy

Page 5: Shape Correspondence through Landmark Sliding

Different types of Shapes

• Supports closed, open, self-crossing and multiple shapes.

Page 6: Shape Correspondence through Landmark Sliding

Input

• Landmarks of template shape

• Landmarks of target shape

• The shape is open or closed

Page 7: Shape Correspondence through Landmark Sliding

Contd..

• The parameters are

is the curve length from u(0) to u(t)

s|L is the curve length from v(0) to v(s)

a|b modulus operation

GOAL : To find s = {s0 , s1 , … sn-1 } such that the shape ‘V’ (target) from it corresponds well to the template shape.

Page 8: Shape Correspondence through Landmark Sliding

Problem

• How to represent the shape?

• We use Catmull Rom Splines since

a. They are smooth

b. They interpolate the landmarks.

Page 9: Shape Correspondence through Landmark Sliding

Problem

• How to represent and initialize the landmarks?

We manually label the landmarks s.t1. The no. of landmarks are same2. The starting pt. is approximately the

same.i.e , we roughly correspond the landmarks

manually.

Page 10: Shape Correspondence through Landmark Sliding

Contd..

Page 11: Shape Correspondence through Landmark Sliding

Problem

• If a landmark moves beyond its neighbours?

We add a constraint

Page 12: Shape Correspondence through Landmark Sliding

Goal

• We try to minimize the cost function,

Ø(s) = d(U,V) + λR(s)

d(U,V) -> landmark based shape difference

R(s) -> representation Error

λ -> Regularization Factor

Page 13: Shape Correspondence through Landmark Sliding

Contd..

L Thin Plate matrix

λ = 10-3 in our experiments

Page 14: Shape Correspondence through Landmark Sliding

Experiment

Page 15: Shape Correspondence through Landmark Sliding

Open Shapes

• For open curves, we

1. Fix the end points

2. Remove segment between the first and last point while calculating R(s).

Page 16: Shape Correspondence through Landmark Sliding

Experiment for open shapes

Page 17: Shape Correspondence through Landmark Sliding

Multiple Curves

1. ‘L’ is calculated taking all the curves.

2. R(s) is calculated seperately for each curve.

Page 18: Shape Correspondence through Landmark Sliding

Experiment for multiple curves

Page 19: Shape Correspondence through Landmark Sliding

Multiple Shape Correspondence

• We have a set of samples We have to find an average shape to which all the shapes corresponds well.

• We do it by1. Taking average of all the shapes using

procustes analysis2. Slide the shapes w.r.t to the average shape3. Repeat the above process.

Page 20: Shape Correspondence through Landmark Sliding

Experiment

Page 21: Shape Correspondence through Landmark Sliding

Conclusion

• Works for all types of shapes

• It considers both global shape deformation and local geometric features unlike the previous methods.