Introduction to Computer Vision - Brown...
Transcript of Introduction to Computer Vision - Brown...
![Page 1: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/1.jpg)
CS143 Intro to
Computer Vision
Brown University
Introduction to Computer
Vision
Michael J. Black
Object Recognition
![Page 2: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/2.jpg)
News
• Last class on Wednesday.
• Attendance will be taken.
• Course evaluation(s).
• Reflections on vision.
![Page 3: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/3.jpg)
vs.
• Bayes rule:
posterior ratio likelihood ratio prior ratio
![Page 4: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/4.jpg)
• Representation
– How to represent an object category
• Learning
– How to form the classifier, given training data
• Recognition
– How the classifier is to be used on novel data
![Page 5: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/5.jpg)
![Page 6: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/6.jpg)
feature detection
& representation
image representation
![Page 7: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/7.jpg)
feature detection
& representation
image representation
![Page 8: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/8.jpg)
• Regular grid
– Vogel & Schiele, 2003
– Fei-Fei & Perona, 2005
![Page 9: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/9.jpg)
• Regular grid
– Vogel & Schiele, 2003
– Fei-Fei & Perona, 2005
• Interest point detector
– Csurka, et al. 2004
– Fei-Fei & Perona, 2005
– Sivic, et al. 2005
![Page 10: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/10.jpg)
Normalize
patch
Detect patches
[Mikojaczyk and Schmid ’02]
[Mata, Chum, Urban & Pajdla, ’02]
[Sivic & Zisserman, ’03]
Compute
SIFT descriptor
[Lowe’99]
Slide credit: Josef Sivic
![Page 11: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/11.jpg)
…
![Page 12: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/12.jpg)
…
![Page 13: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/13.jpg)
Vector quantization
…
Slide credit: Josef Sivic
![Page 14: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/14.jpg)
![Page 15: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/15.jpg)
Fei-Fei et al. 2005
![Page 16: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/16.jpg)
…..
frequency
codewords
![Page 17: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/17.jpg)
feature detection
& representation
image representation
![Page 18: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/18.jpg)
![Page 19: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/19.jpg)
w
N
c
Prior prob. of
the object classes
Image likelihood
given the class
Csurka et al. 2004
Object class
decision
c: category of the image
w: patch in an image N patches
![Page 20: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/20.jpg)
?
![Page 21: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/21.jpg)
Problem with bag-of-words
• All have equal probability for bag-of-words methods
• Location information is important
![Page 22: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/22.jpg)
Model: Parts and Structure
![Page 23: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/23.jpg)
Representation
• Object as set of parts
– Generative representation
• Model:
– Relative locations between parts
– Appearance of part
• Issues:
– How to model location
– How to represent appearance
– Sparse or dense (pixels or regions)
– How to handle occlusion/clutter
Figure from [Fischler & Elschlager 73]
![Page 24: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/24.jpg)
Sparse representation
+ Computationally tractable (105 pixels 101 -- 102 parts)
+ Generative representation of class
+ Avoid modeling global variability
+ Success in specific object recognition
- Throw away most image information
- Parts need to be distinctive to separate from other classes
![Page 25: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/25.jpg)
Region operators
– Local maxima of
interest operator
function
– Can give scale/
orientation invariance
Figures from [Kadir, Zisserman and Brady 04]
![Page 26: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/26.jpg)
The correspondence problem
• Model with P parts
• Image with N possible assignments for each part
• Consider mapping to be 1-1
• NP combinations!!!
![Page 27: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/27.jpg)
• Cartesian – E.g. Gaussian distribution
– Parameters of model, mean and cov
– Independence corresponds to zeros in cov
– Burl et al. ’96, Weber et al. ‘00, Fergus et al. ’03
• Polar – Convenient for
invariance to rotation
Explicit shape model
Mikolajczyk et al., CVPR ‘06
![Page 28: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/28.jpg)
Representation of appearance
• Dependency structure
– Often assume each part’s
appearance is independent
– Common to assume independence with location
• Needs to handle intra-class variation
– Task is no longer matching of
descriptors
– Implicit variation (VQ to get discrete appearance)
– Explicit model of appearance (e.g.
Gaussians in SIFT space)
![Page 29: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/29.jpg)
Representation of appearance
• Invariance needs to match that of
shape model
• Insensitive to small shifts in
translation/scale
– Compensate for jitter of features
– e.g. SIFT
• Illumination invariance
– Normalize out
![Page 30: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/30.jpg)
Appearance representation
• Decision trees
Figure from Winn &
Shotton, CVPR ‘06
• SIFT
• PCA
[Lepetit and Fua CVPR 2005]
![Page 31: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/31.jpg)
Background clutter
• Explicit model – Generative model for clutter as well as foreground
object
• Use a sub-window – At correct position,
no clutter is present
![Page 32: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/32.jpg)
CS143 Intro to
Computer Vision
Brown University
Representing Objects
Fei-Fei Li.
![Page 33: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/33.jpg)
![Page 34: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/34.jpg)
Demo (2)
![Page 35: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/35.jpg)
Demo (3)
![Page 36: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/36.jpg)
Demo (4)
![Page 37: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/37.jpg)
Demo: efficient methods
![Page 38: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/38.jpg)
CS143 Intro to
Computer Vision
Brown University
![Page 39: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/39.jpg)
CS143 Intro to
Computer Vision
Brown University
![Page 40: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/40.jpg)
CS143 Intro to
Computer Vision
Brown University
![Page 41: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/41.jpg)
CS143 Intro to
Computer Vision
Brown University
Parts Learn parts
from
examples.
Find interesting
points
(structure
tensor), find
similar ones,
use PCA to
model them.
Fro
m:
Rob F
erg
us h
ttp://w
ww
.robots
.ox.a
c.u
k/%
7E
ferg
us/
![Page 42: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/42.jpg)
CS143 Intro to
Computer Vision
Brown University
Shape Given a “vocabulary” of parts,
learn a model of their spatial
relationships
Fro
m:
Rob F
erg
us h
ttp://w
ww
.robots
.ox.a
c.u
k/%
7E
ferg
us/
![Page 43: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/43.jpg)
CS143 Intro to
Computer Vision
Brown University
Recognizing Objects
Fei-Fei Li.
![Page 44: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/44.jpg)
Implicit shape model
Spatial occurrence distributions x
y
s
x
y
s x
y
s
x
y
s
Probabilistic
Voting Interest Points Matched Codebook
Entries Recognition
Learning
• Learn appearance codebook – Cluster over interest points on
training images
• Learn spatial distributions – Match codebook to training images
– Record matching positions on object
– Centroid is given
• Use Hough space voting to find object
• Leibe and Schiele ’03,’05
![Page 45: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/45.jpg)
~100 Things We’ve Learned
Pinhole camera
Perspective projection
Orthographic projection
Weak perspective
PCA
Eigenvalues
Eigenvectors
Inpainting
Markov random field
Particle filter
Image statistics
Continuation method
Graduated non-convexity
MAP estimate
Gaussian pyramid
Laplacian pyramid
Matlab
Linear filtering
Convolution
Gaussian
Gradient
Dimensionality reduction
Monte Carlo sampling
Convolution
Correlation
Projection
Finite differences
Steerable filter
Gradient magnitude
DoG
Template matching
Normalized correlation
SSD
Subspaces
Basis image
SVD
Eigenfaces
Histogram
![Page 46: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/46.jpg)
~100 Things We’ve Learned
Random variable
Marginalize
Expectation
Statistical independence
Conditional independence
Joint probability
Conditional probability
Bayes Theorem
Likelihood
Prior
Classifier
Tracking
Regularization
Stereo
Posterior
Covariance
Structure tensor
Mahalanobis distance
Whitening
Denoising
Motion field
Optical flow
Taylor series
Brightness constancy
OFCE
Aperture problem
Outliers Rectification Epipole
Affine
Least squares
Generative model
Warping
Interpolation
Super resolution
Occlusion
Robust statistics
Influence function
Breakdown point
Gradient descent
Annealing
Discontinuities
Binocular disparity
![Page 47: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/47.jpg)
~100 Things We’ve Learned
So are we done?
![Page 48: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/48.jpg)
Timeline
Vision as AI
1975-1985
Lofty goals and early excitement.
Early view (50’s-60’s): Minsky thought the
vision sub-problem of AI could be solved by a single PhD student in a single
summer. Done. Move on.
![Page 49: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/49.jpg)
Timeline
Vision as AI
1975-1985
Shattered dreams and early disappointment.
![Page 50: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/50.jpg)
Timeline
Physics &
Geometry
1975-1985 1985-1995
Regroup, focus on the basics
* metric reconstruction, quantitative evaluation.
* optimization methods.
![Page 51: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/51.jpg)
Timeline
Learning &
Applications
1975-1985 1985-1995 1995-2005
Trends: big disks, digital cameras, Firewire, fast processors, desktop
video.
Machine learning provides a new grounding.
![Page 52: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/52.jpg)
Timeline
Learning &
Applications
1975-1985 1985-1995 1995-2005
Real applications. Eg for optical flow
What Dreams May Come 1998,
The Matrix 1999
![Page 53: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/53.jpg)
Timeline
Integration
& Inference
1975-1985 1985-1995 1995-2005 2005-2015
Return to some of the early goals with new tools.
![Page 54: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/54.jpg)
Timeline
Integration
& Inference
Bayesian inference &
Statistical models
1975-1985 1985-1995 1995-2005 2005-2015
Levitt & Binford
![Page 55: Introduction to Computer Vision - Brown Universitycs.brown.edu/courses/cs143/2009/ObjectRecogPart2.pdf · • Representation – How to represent an object category • Learning –](https://reader033.fdocuments.in/reader033/viewer/2022041716/5e4b4f4aa7dac566602d3814/html5/thumbnails/55.jpg)
What is still far off?
* Here “vision” problem is trivial but explanation is hard.
Motion interpretation.
Heider&Simmel, 1944
<Play>