CS 44957495 Computer Vision - PowerPoint PPT Presentation

1 / 26
About This Presentation
Title:

CS 44957495 Computer Vision

Description:

Cameras and Geometric Camera Models. Jim Rehg ... Basic abstraction is the pinhole camera. lenses required to ensure image is not too dark ... – PowerPoint PPT presentation

Number of Views:38
Avg rating:3.0/5.0
Slides: 27
Provided by: FrankDe62
Category:
Tags: computer | vision

less

Transcript and Presenter's Notes

Title: CS 44957495 Computer Vision


1
CS 4495/7495Computer Vision
  • Cameras and Geometric Camera Models
  • Jim Rehg
  • (Borrowed liberally from Frank Dellaert and
    Forsyth Ponce)

2
Outline
  • Pinhole Cameras
  • Cameras with Lenses
  • Research Highlight Perspective cues for scene
    understanding
  • Next lecture Camera Calibration

3
Cameras
  • First photograph due to Niepce
  • Basic abstraction is the pinhole camera
  • lenses required to ensure image is not too dark
  • various other abstractions can be applied

4
Pinhole cameras
  • Abstract camera model - box with a small hole in
    it
  • Pinhole cameras work in practice

5
The equation of projection
Weird and difficult diagram in the book
6
Pinhole Camera Model
Image plane
Focal length f
Center of projection
7
Pinhole Camera Model
Image plane
Virtual Image
8
Pinhole Camera Model
Image plane
Virtual Image
9
Distant objects are smaller
C
B
10
Pinhole Camera Summary
k
P
p
i
C
Q
f
q
O
j
11
Parallel lines meet
12
Vanishing points
  • each set of parallel lines (direction) meets at
    a different point
  • The vanishing point for this direction
  • Sets of parallel lines on the same plane lead to
    collinear vanishing points.
  • The line is called the horizon for that plane
  • Good ways to spot faked images
  • scale and perspective dont work
  • vanishing points behave badly
  • supermarket tabloids are a great source.

13
(No Transcript)
14
Geometric properties of projection
  • Points go to points
  • Lines go to lines
  • Planes go to whole image
  • Polygons go to polygons
  • Degenerate cases
  • line through focal point to point
  • plane through focal point to line

15
Weak perspective
  • perspective effects, but not over the scale of
    individual objects
  • collect points into a group at about the same
    depth, then divide each point by the depth of its
    group
  • easy
  • - wrong

16
Orthographic projection
17
  • Cameras with Lenses

18
Pinhole too big - many directions are
averaged, blurring the image Pinhole too
small- diffraction effects blur the
image Generally, pinhole cameras are dark,
because a very small set of rays from a
particular point hits the screen.
19
The reason for lenses
20
The thin lens
21
Focussing
http//www.theimagingsource.com
22
Spherical aberration
23
Vignetting
24
Other annoying phenomena
  • Chromatic aberration
  • Light at different wavelengths follows different
    paths hence, some wavelengths are defocussed
  • Machines coat the lens
  • Humans live with it
  • Geometric phenomena
  • Radial Distortion
  • Barrel distortion

25
Geometric Context from a Single Image
Hoiem, Efros, Hebert
26
Automatic Pop-up
27
Putting Objects in Perspective
28
Other stuff in Chapter 1
  • Background reading
  • Human eye
  • Sensing
  • CCD Cameras
  • Sensor Models
Write a Comment
User Comments (0)
About PowerShow.com