![Page 1: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/1.jpg)
Computer Vision GroupUniversity 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
![Page 2: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/2.jpg)
Computer Vision GroupUniversity of California Berkeley
From images/video to objects
Labeled sets: tiger, grass etc
![Page 3: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/3.jpg)
Computer Vision GroupUniversity of California Berkeley
![Page 4: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/4.jpg)
Computer Vision GroupUniversity of California Berkeley
![Page 5: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/5.jpg)
Computer Vision GroupUniversity of California Berkeley
Consistency
A
B C
• A,C are refinements of B• A,C are mutual refinements • A,B,C represent the same percept
• Attention accounts for differences
Image
BG L-bird R-bird
grass bush
headeye
beakfar body
headeye
beak body
Perceptual organization forms a tree:
Two segmentations are consistent when they can beexplained by the samesegmentation tree (i.e. theycould be derived from a single perceptual organization).
![Page 6: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/6.jpg)
Computer Vision GroupUniversity of California Berkeley
Outline
• Finding boundaries
• Recognizing objects
• Recognizing actions
![Page 7: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/7.jpg)
Computer Vision GroupUniversity of California Berkeley
Finding boundaries: Is texture a problem or a solution?
image orientation energy
![Page 8: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/8.jpg)
Computer Vision GroupUniversity 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.
![Page 9: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/9.jpg)
Computer Vision GroupUniversity of California Berkeley
Orientation Energy
• Gaussian 2nd derivative and its Hilbert pair
•
• Can detect combination of bar and edge features [Perona & Malik 90]
22 )()( evenodd fIfIOE
![Page 10: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/10.jpg)
Computer Vision GroupUniversity of California Berkeley
Texture gradient = Chi square distance between texton histograms in half disks across edge
Texture gradient = Chi square distance between texton histograms in half disks across edge
i
j
k
K
m ji
jiji mhmh
mhmhhh
1
22
)()(
)]()([
2
1),(Chi-square
0.1
0.8
![Page 11: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/11.jpg)
Computer Vision GroupUniversity of California Berkeley
![Page 12: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/12.jpg)
Computer Vision GroupUniversity of California Berkeley
![Page 13: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/13.jpg)
Computer Vision GroupUniversity of California Berkeley
ROC curve for local boundary detection
![Page 14: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/14.jpg)
Computer Vision GroupUniversity of California Berkeley
Outline
• Finding boundaries
• Recognizing objects
• Recognizing actions
![Page 15: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/15.jpg)
Computer Vision GroupUniversity of California Berkeley
Biological Shape
• D’Arcy Thompson: On Growth and Form, 1917– studied transformations between shapes of organisms
![Page 16: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/16.jpg)
Computer Vision GroupUniversity of California Berkeley
Deformable Templates: Related Work
• Fischler & Elschlager (1973)
• Grenander et al. (1991)
• von der Malsburg (1993)
![Page 17: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/17.jpg)
Computer Vision GroupUniversity of California Berkeley
Matching Framework
• Find correspondences between points on shape
• Fast pruning
• Estimate transformation & measure similarity
model target
...
![Page 18: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/18.jpg)
Computer Vision GroupUniversity of California Berkeley
Comparing Pointsets
![Page 19: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/19.jpg)
Computer Vision GroupUniversity of California Berkeley
Shape ContextCount the number of points inside each bin, e.g.:
Count = 4
Count = 10
...
Compact representation of distribution of points relative to each point
![Page 20: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/20.jpg)
Computer Vision GroupUniversity of California Berkeley
Shape Context
![Page 21: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/21.jpg)
Computer Vision GroupUniversity of California Berkeley
Comparing Shape Contexts
Compute matching costs using Chi Squared distance:
Recover correspondences by solving linear assignment problem with costs Cij
[Jonker & Volgenant 1987]
![Page 22: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/22.jpg)
Computer Vision GroupUniversity of California Berkeley
Matching Framework
• Find correspondences between points on shape
• Fast pruning
• Estimate transformation & measure similarity
model target
...
![Page 23: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/23.jpg)
Computer Vision GroupUniversity of California Berkeley
Fast pruning
• Find best match for the shape context at only a few random points and add up cost
),(minarg
),(),(
2*
*
1
2
ui
jqueryui
ij
query
r
jiquery
SCSCSC
SCSCSSdist
![Page 24: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/24.jpg)
Computer Vision GroupUniversity of California Berkeley
Matching Framework
• Find correspondences between points on shape
• Fast pruning
• Estimate transformation & measure similarity
model target
...
![Page 25: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/25.jpg)
Computer Vision GroupUniversity 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)
![Page 26: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/26.jpg)
Computer Vision GroupUniversity of California Berkeley
MatchingExample
model target
![Page 27: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/27.jpg)
Computer Vision GroupUniversity of California Berkeley
Outlier Test Example
![Page 28: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/28.jpg)
Computer Vision GroupUniversity of California Berkeley
Object Recognition Experiments
• Handwritten digits
• COIL 3D objects (Nayar-Murase)
• Human body configurations
• Trademarks
![Page 29: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/29.jpg)
Computer Vision GroupUniversity 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
![Page 30: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/30.jpg)
Computer Vision GroupUniversity 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%
![Page 31: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/31.jpg)
Computer Vision GroupUniversity of California Berkeley
![Page 32: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/32.jpg)
Computer Vision GroupUniversity of California Berkeley
COIL Object Database
![Page 33: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/33.jpg)
Computer Vision GroupUniversity of California Berkeley
Prototypes Selected for 2 Categories
Details in Belongie, Malik & Puzicha (NIPS2000)
![Page 34: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/34.jpg)
Computer Vision GroupUniversity of California Berkeley
Error vs. Number of Views
![Page 35: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/35.jpg)
Computer Vision GroupUniversity of California Berkeley
Human body configurations
![Page 36: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/36.jpg)
Computer Vision GroupUniversity 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
![Page 37: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/37.jpg)
Computer Vision GroupUniversity of California Berkeley
Results
![Page 38: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/38.jpg)
Computer Vision GroupUniversity of California Berkeley
Trademark Similarity
![Page 39: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/39.jpg)
Computer Vision GroupUniversity of California Berkeley
Recognizing objects in scenes
![Page 40: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/40.jpg)
Computer Vision GroupUniversity of California Berkeley
Outline
• Finding boundaries
• Recognizing objects
• Recognizing actions
![Page 41: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/41.jpg)
Computer Vision GroupUniversity 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
![Page 42: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/42.jpg)
Computer Vision GroupUniversity 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
![Page 43: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/43.jpg)
Computer Vision GroupUniversity 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
![Page 44: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/44.jpg)
Computer Vision GroupUniversity of California Berkeley
Tracking by Repeated Finding
![Page 45: Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,](https://reader030.vdocuments.us/reader030/viewer/2022032704/56649d4b5503460f94a28ff7/html5/thumbnails/45.jpg)
Computer Vision GroupUniversity 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.