Introduction to Computer Vision

jabgoldfishAI and Robotics

Oct 19, 2013 (3 years and 7 months ago)

96 views

Introduction to Computer Vision


CS223B, Winter 2005


1/25/2005

Introduction to Computer Vision

2

Richard Szeliski


Guest Lecturer


Ph. D., Carnegie Mellon, 1988


Researcher, Cambridge Research

Lab at DEC, 1990
-
1995


Senior Researcher, Interactive

Visual Media Group, Microsoft, 1995
-


Research interests:


computer vision (stereo, motion),

computer graphics (image
-
based rendering),
parallel programming

What is Computer Vision?

1/25/2005

Introduction to Computer Vision

4

What is Computer Vision?


Image Understanding (AI, behavior)


A sensor modality for robotics


Computer emulation of human vision


Inverse of Computer Graphics






Computer

vision

World

model

Computer

graphics

World

model

1/25/2005

Introduction to Computer Vision

5

Intersection of Vision and Graphics

modeling

-

shape

-

light

-

motion

-

optics

-

images


IP

animation

rendering

user
-
interfaces

surface design

Computer Graphics

shape estimation

motion estimation

recognition

2D modeling

modeling

-

shape

-

light

-

motion

-

optics

-

images


IP

Computer Vision

1/25/2005

Introduction to Computer Vision

6

Computer Vision
[Trucco&Verri’98]

1/25/2005

Introduction to Computer Vision

7

Image
-
Based Modeling




Images (2D)

Geometry (3D)

shape

Photometry

appearance

+

graphics

vision

image processing

2.1

Geometric
image formation

2.2

Photometric
image formation

3

Image
processing

4

Feature
extraction

5

Camera
calibration

6

Structure

from motion

7

Image

alignment


8

Mosaics


9

Stereo
correspondence

11

Model
-
based
reconstruction

12

Photometric
recovery

14

Image
-
based
rendering

1/25/2005

Introduction to Computer Vision

11

Syllabus

Image Transforms / Representations


filters, pyramids, steerable filters


warping and resampling


blending


image statistics, denoising/coding


edge and feature detection

1/25/2005

Introduction to Computer Vision

12

Image Pyramid

Bandpass Images

Lowpass Images

1/25/2005

Introduction to Computer Vision

13

Pyramid Blending

1/25/2005

Introduction to Computer Vision

14

Parametric (global) warping

Examples of parametric warps:

translation

rotation

aspect

affine

perspective

cylindrical

1/25/2005

Introduction to Computer Vision

15

Syllabus

Optical Flow


least squares regression


iterative, coarse
-
to
-
fine


parametric


robust flow and mixture models


layers, EM

1/25/2005

Introduction to Computer Vision

16

Image Morphing

1/25/2005

Introduction to Computer Vision

17

Syllabus

Projective geometry


points, lines, planes, transforms

Camera calibration and pose


point matching and tracking


lens distortion

Image registration


mosaics

1/25/2005

Introduction to Computer Vision

18

Panoramic Mosaics







+ + … +



=

1/25/2005

Introduction to Computer Vision

19

Syllabus

3D structure from motion


two frame techniques


factorization of shape and motion


bundle adjustment

1/25/2005

Introduction to Computer Vision

20

3D Shape Reconstruction

Debevec, Taylor, and Malik, SIGGRAPH 1996


1/25/2005

Introduction to Computer Vision

21

Face Modeling

1/25/2005

Introduction to Computer Vision

22

Syllabus

Stereo


correspondence


local methods


global optimization

1/25/2005

Introduction to Computer Vision

23

View Morphing

Morph between pair of images using epipolar
geometry
[Seitz & Dyer, SIGGRAPH’96]

1/25/2005

Introduction to Computer Vision

24

Z
-
keying: mix live and synthetic

Takeo Kanade, CMU (
Stereo Machine
)

1/25/2005

Introduction to Computer Vision

25

Virtualized Reality
TM

Takeo Kanade, CMU


collect video from 50+ stream

reconstruct 3D model sequences







http://www.cs.cmu.edu/afs/cs/project/VirtualizedR/www/VirtualizedR.html

1/25/2005

Introduction to Computer Vision

26

Virtualized Reality
TM

Takeo Kanade, CMU


generate new video









steerable version used for SuperBowl XXV

“eye vision” system

1/25/2005

Introduction to Computer Vision

27

Syllabus

Tracking


eigen
-
tracking


on
-
line EM


Kalman filter


particle filtering


appearance models


1/25/2005

Introduction to Computer Vision

28

Syllabus

Recognition


subspaces and local invariance features


face recognition


color histograms


textures

Image editing


segmentation


curve tracking

1/25/2005

Introduction to Computer Vision

29

Edge detection and editing

Elder, J. H. and R. M. Goldberg. "Image Editing in the Contour Domain,"

Proc. IEEE: Computer Vision and Pattern Recognition, pp. 374
-
381, June, 1998.


1/25/2005

Introduction to Computer Vision

30

Image Enhancement

High dynamic range photography

[Debevec
et al
.’97; Mitsunaga & Nayar’99]


combine several different exposures together

1/25/2005

Introduction to Computer Vision

31

Syllabus

Image
-
based rendering


Lightfields and Lumigraphs


concentric mosaics


layered models


video
-
based rendering

1/25/2005

Introduction to Computer Vision

32

Concentric Mosaics

Interpolate between several panoramas to give
a 3D depth effect


[Shum & He, SIGGRAPH’99]

1/25/2005

Introduction to Computer Vision

33

Applications


Geometric reconstruction: modeling,
forensics, special effects (ILM, RealVis,2D3)


Image and video editing (Avid, Adobe)


Webcasting and Indexing Digital Video
(Virage)


Scientific / medical applications (GE)

1/25/2005

Introduction to Computer Vision

34

Applications


Tracking and surveillance (Sarnoff)


Fingerprint recognition (Digital Persona)


Biometrics / iris scans (Iridian Technologies)


Vehicle safety (MobilEye)


Drowning people (VisionIQ Inc)


Optical motion capture (Vicon)

1/25/2005

Introduction to Computer Vision

35

Projects

Let’s look at what students have done in
previous years …


Stanford


http://www.stanford.edu/class/cs223b/winter01
-
02/projects.html


CMU


http://www
-
2.cs.cmu.edu/~ph/869/www/869.html


UW
http://www.cs.washington.edu/education/courses/cse590ss/01wi/


GA Tech


http://www.cc.gatech.edu/classes/AY2002/cs4480_spring/