Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Object Recognition with Pictorial Structures                Pedro F. Felzenszwalb                University of Chicago    ...
Pictorial structuresPart-based representation: • Each part models local visual properties. • “Springs” model spatial relat...
• Model is represented by a graph G = (V, E).   – V = {v1, . . . , vn} are the parts.   – (vi, vj ) ∈ E indicates a connec...
Efficient minimization                                                                                    n          L∗ = ...
Distance transform Given a set of points on a grid P ⊆ G,the quadratic distance transform of P is,          DP (q) = min |...
Generalized distance transformGiven a function f : G → R,                 Df (q) = min ||q − p||2 + f (p)                 ...
1D case:      Df (q) = minp∈G (q − p)2 + f (p)For each p, Df (q) is below the parabola rooted at (p, f (p)).Df (q) is defin...
There is a simple geometric algorithm that computes Df (p) inO(h) time for the 1D case. – similar to Graham’s scan convex ...
Simple face model• Locations are positions in the image grid.• Match cost mi(li) for placing part i at li.• Central part v...
Efficient minimization                                                                               n                nL∗ ...
Matching results                   10
Matching results                   11
Summary• Generic framework for part-based modeling.• Global minimization for deformable objects can be fast.• Soft detecti...
Upcoming SlideShare
Loading in …5
×

Object recognition with pictorial structures

1,627 views

Published on

Published in: Technology, Business
  • Login to see the comments

Object recognition with pictorial structures

  1. 1. Object Recognition with Pictorial Structures Pedro F. Felzenszwalb University of Chicago pff@cs.uchicago.edu Joint work with Daniel P. Huttenlocher
  2. 2. Pictorial structuresPart-based representation: • Each part models local visual properties. • “Springs” model spatial relationships. • Joint estimation of part locations. – No hard detection of parts or features. – No initialization parameters. 1
  3. 3. • Model is represented by a graph G = (V, E). – V = {v1, . . . , vn} are the parts. – (vi, vj ) ∈ E indicates a connection between parts.• mi(li) is the cost of placing part i at location li.• dij (li, lj ) is a deformation cost.• Optimal location for object is given by L∗ = (l1, . . . , ln), ∗ ∗   n L∗ = argmin  mi(li) + dij (li, lj )   L i=1 (vi,vj )∈E 2
  4. 4. Efficient minimization   n L∗ = argmin  mi(li) + dij (li, lj )   L i=1 (vi,vj )∈E• n parts and h locations gives hn configurations.• If graph is a tree we can use dynamic programming. – O(nh2), much better but still slow.• If dij (li, lj ) = ||Tij (li) − Tji(lj )||2 can use DT. – O(nh), as good as matching each part separately!! 3
  5. 5. Distance transform Given a set of points on a grid P ⊆ G,the quadratic distance transform of P is, DP (q) = min ||q − p||2 p∈P P DP 4
  6. 6. Generalized distance transformGiven a function f : G → R, Df (q) = min ||q − p||2 + f (p) p∈G – for each location q, find nearby location p with f (p) small. – equals DT of points P if f is an indicator function.  0 if p ∈ P f (p) = . ∞ otherwise 5
  7. 7. 1D case: Df (q) = minp∈G (q − p)2 + f (p)For each p, Df (q) is below the parabola rooted at (p, f (p)).Df (q) is defined by the lower envelope of h parabolas. 1 f ( ) 2 f ( ) § h 1 f ( ) 0 f ( ) § . . . . . . . . . . . . . 0 1 2 h 1 6
  8. 8. There is a simple geometric algorithm that computes Df (p) inO(h) time for the 1D case. – similar to Graham’s scan convex hull algorithm. – about 20 lines of C code.The 2D case is “separable”, it can be solved by sequential 1Dtransformations along rows and columns of the grid.See Distance Transforms of Sampled Functions, Felzen-szwalb and Huttenlocher. 7
  9. 9. Simple face model• Locations are positions in the image grid.• Match cost mi(li) for placing part i at li.• Central part v1 - the nose.• Each part has an ideal position pi relative to nose. – Let T1i(l1) = l1 + pi, n n E(l1, . . . , ln) = mi(li) + ||li − T1i(l1)||2 i=1 i=2 8
  10. 10. Efficient minimization   n nL∗ = argmin  mi(li) + ||li − T1i(l1)||2 L i=1 i=2   nL∗ = argmin m1(l1) + mi(li) + ||li − T1i(l1)||2 L i=2   n ∗l1 = argmin m1(l1) + min(mi(li) + ||li − T1i(l1)||2) l1 i=2 li   n ∗l1 = argmin m1(l1) + Dmi (T1i(l1)) l1 i=2 9
  11. 11. Matching results 10
  12. 12. Matching results 11
  13. 13. Summary• Generic framework for part-based modeling.• Global minimization for deformable objects can be fast.• Soft detection avoids unnecessary early decisions.• Partial occlusion is handled automatically. 12

×