Title: Computer%20vision%20class,%20%20fast-forward
1http//www.ai.mit.edu/courses/6.801/
2(No Transcript)
3(No Transcript)
4(No Transcript)
5(No Transcript)
6(No Transcript)
7(No Transcript)
8Vision
- What does it mean, to see? to know what is
where by looking. - How to discover from images what is present in
the world, where things are, what actions are
taking place.
from Marr, 1982
9Computer vision class, fast-forward
10Images and image formation
11Cameras, lenses, and sensors
- Pinhole cameras
- Lenses
- Projection models
- Geometric camera parameters
From Computer Vision, Forsyth and Ponce,
Prentice-Hall, 2002.
12Radiometry
Wolfgang Lucht
http//geography.bu.edu/brdf/brdfexpl.html
13Color
From Foundations of Vision, by Brian Wandell,
Sinauer Assoc., 1995
14Low-level vision
15Image filtering
- Review of linear systems, convolution
- Bandpass filter-based image representations
- Probabilistic models for images
Image
Oriented, multi-scale representation
16Non-linear filtering, and applications
17Models of texture
18Shape from shading
Shape from shading, Horn and Brooks, MIT Press,
1986
19Bayesian framework for vision
Gahan Wilsons Still Weird, Forge, 1994
20Bayesian framework for vision
Coincidental appearance of face profile in rock?
http//www.cs.dartmouth.edu/whites/old_man.html
21Bayesian framework for vision
Coincidental appearance of faces in rock?
http//bensguide.gpo.gov/3-5/symbols/print/mountru
shmore.html
22Edge detection and optical flow
M. Heath, S. Sarkar, T. Sanocki, and K.W. Bowyer,
"A Robust Visual Method for Assessing the
Relative Performance of Edge-Detection
Algorithms" IEEE Transactions on Pattern Analysis
and Machine Intelligence, Vol. 19, No. 12,
December 1997, pp. 1338-1359.
23Edge detection and optical flow
True optical flow
Images
in "Statistical Theories of the Brain", edited
by R. Rao, B. Olshausen, and M. Lewicki, MIT
Press, 2001
Estimated optical flow
24Learning and vision
25Statistical classifiers
- MIT Media Lab face localization results.
- Applications database search, human machine
interaction, video conferencing.
26Support vector machines and boosting
Large-margin classifier
www.support-vector.net/nello.html
27Support vector machines and boosting
The kernel trick
www.support-vector.net/nello.html
28Applications
- Computer vision for computer games
29Computer vision applicationsas ocean-going
vessels
30Game Decathlete
31Optical-flow-based Decathlete figure motion
analysis
32Decathlete 100m hurdles
33Decathlete javelin throw
34Decathlete javelin throw
35video
36Nintendo Game Boy Camera
- Several million sold (most of any digital
camera). Imaging chip is Mitsubishi Electrics
Artificial Retina CMOS detector.
37video
38The course, in broad categories
- Images and image formation
- Geometry
- Low-level vision
- High-level vision
- Implementations and applications