1. Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes, T. Leung, D. Martin, G. Mori, J. Puzicha, J.Shi, X. Ren

2. Computer Vision Group University of California Berkeley From images/video to objects Labeled sets: tiger, grass etc

3. Computer Vision Group University of California Berkeley

4. Computer Vision Group University of California Berkeley

5. Computer Vision Group University of California Berkeley Consistency A BC A,C are refinements of B A,C are mutual refinements A,B,C represent the same percept Attention accounts for differences Image BGL-birdR-bird grass bush head eye beak far body head eye beak body Perceptual organization forms a tree: Two segmentations are consistent when they can be explained by the same segmentation tree (i.e. they could be derived from a single perceptual organization).

6. Computer Vision Group University of California Berkeley Outline Finding boundaries Recognizing objects Recognizing actions

7. Computer Vision Group University of California Berkeley Finding boundaries: Is texture a problem or a solution? imageorientation energy

8. Computer Vision Group University of California Berkeley Statistically optimal contour detection Use humans to segment a large collection of natural images. Train a classifier for the contour/non-contour classification using orientation energy and texture gradient as features.

9. Computer Vision Group University of California Berkeley Orientation Energy Gaussian 2nd derivative and its Hilbert pair Can detect combination of bar and edge features [Perona & Malik 90]

10. Computer Vision Group University of California Berkeley Texture gradient = Chi square distance between texton histograms in half disks across edge i j k Chi-square 0.1 0.8

11. Computer Vision Group University of California Berkeley

12. Computer Vision Group University of California Berkeley

13. Computer Vision Group University of California Berkeley ROC curve for local boundary detection

14. Computer Vision Group University of California Berkeley Outline Finding boundaries Recognizing objects Recognizing actions

15. Computer Vision Group University of California Berkeley Biological Shape D’Arcy Thompson: On Growth and Form, 1917 –studied transformations between shapes of organisms

16. Computer Vision Group University of California Berkeley Deformable Templates: Related Work Fischler & Elschlager (1973) Grenander et al. (1991) von der Malsburg (1993)

17. Computer Vision Group University of California Berkeley Matching Framework Find correspondences between points on shape Fast pruning Estimate transformation & measure similarity modeltarget...

18. Computer Vision Group University of California Berkeley Comparing Pointsets

19. Computer Vision Group University of California Berkeley Shape Context Count the number of points inside each bin, e.g.: Count = 4 Count = 10... FCompact representation of distribution of points relative to each point

20. Computer Vision Group University of California Berkeley Shape Context

21. Computer Vision Group University of California Berkeley Comparing Shape Contexts Compute matching costs using Chi Squared distance: Recover correspondences by solving linear assignment problem with costs C ij [Jonker & Volgenant 1987]

22. Computer Vision Group University of California Berkeley Matching Framework Find correspondences between points on shape Fast pruning Estimate transformation & measure similarity modeltarget...

23. Computer Vision Group University of California Berkeley Fast pruning Find best match for the shape context at only a few random points and add up cost

24. Computer Vision Group University of California Berkeley Matching Framework Find correspondences between points on shape Fast pruning Estimate transformation & measure similarity modeltarget...

25. Computer Vision Group University of California Berkeley 2D counterpart to cubic spline: Minimizes bending energy: Solve by inverting linear system Can be regularized when data is inexact Thin Plate Spline Model Duchon (1977), Meinguet (1979), Wahba (1991)

26. Computer Vision Group University of California Berkeley Matching Example modeltarget

27. Computer Vision Group University of California Berkeley Outlier Test Example

28. Computer Vision Group University of California Berkeley Object Recognition Experiments Handwritten digits COIL 3D objects (Nayar-Murase) Human body configurations Trademarks

29. Computer Vision Group University of California Berkeley Terms in Similarity Score Shape Context difference Local Image appearance difference –orientation –gray-level correlation in Gaussian window –… (many more possible) Bending energy

30. Computer Vision Group University of California Berkeley Handwritten Digit Recognition MNIST 60 000: –linear: 12.0% –40 PCA+ quad: 3.3% –1000 RBF +linear: 3.6% –K-NN: 5% –K-NN (deskewed) : 2.4% –K-NN (tangent dist.) : 1.1% –SVM: 1.1% –LeNet 5: 0.95% MNIST 600 000 (distortions): –LeNet 5: 0.8% –SVM: 0.8% –Boosted LeNet 4: 0.7% MNIST 20 000: –K-NN, Shape Context matching: 0.63%

31. Computer Vision Group University of California Berkeley

32. Computer Vision Group University of California Berkeley COIL Object Database

33. Computer Vision Group University of California Berkeley Prototypes Selected for 2 Categories Details in Belongie, Malik & Puzicha (NIPS2000)

34. Computer Vision Group University of California Berkeley Error vs. Number of Views

35. Computer Vision Group University of California Berkeley Human body configurations

36. Computer Vision Group University of California Berkeley Deformable Matching Kinematic chain-based deformation model Use iterations of correspondence and deformation Keypoints on exemplars are deformed to locations on query image

37. Computer Vision Group University of California Berkeley Results

38. Computer Vision Group University of California Berkeley Trademark Similarity

39. Computer Vision Group University of California Berkeley Recognizing objects in scenes

40. Computer Vision Group University of California Berkeley Outline Finding boundaries Recognizing objects Recognizing actions

41. Computer Vision Group University of California Berkeley Examples of Actions Movement and posture change –run, walk, crawl, jump, hop, swim, skate, sit, stand, kneel, lie, dance (various), … Object manipulation –pick, carry, hold, lift, throw, catch, push, pull, write, type, touch, hit, press, stroke, shake, stir, turn, eat, drink, cut, stab, kick, point, drive, bike, insert, extract, juggle, play musical instrument (various)… Conversational gesture –point, … Sign Language

42. Computer Vision Group University of California Berkeley Key cues for action recognition “Morpho-kinesics” of action (shape and movement of the body) Identity of the object/s Activity context

43. Computer Vision Group University of California Berkeley Image/Video  Stick figure  Action Stick figures can be specified in a variety of ways or at various resolutions (deg of freedom) –2D joint positions –3D joint positions –Joint angles Complete representation Evidence that it is effectively computable

44. Computer Vision Group University of California Berkeley Tracking by Repeated Finding

45. Computer Vision Group University of California Berkeley Achievable goals in 3 years Reasonable competence at object recognition at crude category level (~1000) Detection/Tracking of humans as kinematic chains, assuming adequate resolution. Recognition of ~10-100 actions and compositions thereof.