Computational Vision

1
Computational Vision

• Lecture 1 Overview Biological Vision
• Jeremy Wyatt

2
What you should be able to do

• Make informed choices about which sort of
  algorithms to apply to solve specific problems.
• Use standard vision libraries or software to
  construct working vision systems.
• Apply algorithms to simplified problems by hand.
• Discuss the advantages and drawbacks of different
  methods, explaining their working.

3
Schedule

• 1 lecture a week, Mondays _at_ 2pm, Muirhead
• 1 lab/lecture a week, Thursdays _at_ 12pm (Robot Lab
  or Chem Eng)
• I am currently away on Monday Oct 3 and Monday
  Nov 14, so there will be no lectures on those
  days

4
Syllabus

• Lectures
• Biological Vision
• Edge detection
• Hough transforms
• Motion/Depth
• Recognising objects
• Recognising events
• Recognising faces
• Visual attention

• Labs
• Matlab tutorials
• Edge detection
• Hough transforms
• Face recognition
• Object recognition

5
Assessment

• 70 1.5 hour unseen exam in May/June
• 30 3 page experimental write-up of one of
  your labs (in pairs)
• (due Dec 7 12 noon)

6
Biological Vision

• Light and image formation
• Retinal Processing
• Colour
• Visual Pathway
• Striate Cortex

7
Visible spectrum

• Humans perceive electromagnetic radiation with
  wavelengths 380-760nm (1 nm 10-9 m)

0.1nm 10nm
1000nm
8
Image Formation

• f is the focal length (in metres)
• is the power of the lens (in dioptres)
• Human eye has power 59 dioptres

Image plane
Lens
Light rays
f
9
Image Formation

• Most of the refractive power of the human eye
  comes from the air-cornea boundary(49 of 59
  dioptres)
• As an object moves closer the power of the lens
  must increase to accommodate
• So if the object is infinitely far away
• But if it is 1m away the lens must
• change shape to produce a sharp image

u
v
10
Image Formation

• As an object moves in world how does it move
  across the image plane?
• If the image plane is curved then as q gets
  larger this becomes a worse and worse
  approximation

h
v
q
i
u
11
Retinal Processing

• 120m rods, 6m cones

12
Retinal Processing

• Amacrine and horizontal cells integrate receptor
  outputs
• More rods connect to each ganglion cells less
  acuity, but greater sensitivity
• Ganglions have receptive fields

13
Types of Ganglion cell

• Centre surround cells

OFF Cell
ON Cell
Light
OFF area
ON area
ON area
OFF area
Time
Light spot
14
Perceptual effects
15
Colour

• Two theories/systems
• Trichromatic (Young-Helmholtz)
• Explains
• How we discriminate wavelengths 2nm in difference
• How we can match a mixture of wavelengths to a
  single colour
• Some types of colour blindness

16
Colour

• Trichromatic theory cant explain colour blending

Bluey green
Orange
?
Greeny red?
?
Yellowy blue?
17
Opponent Colour Theory

• Ganglion ON cells sensitive to outputs of cones

OFF
ON
18
Opponent colour theory
Red on
Green off
Yellow on
Excitatory
Inhibitory
19
After images
20
Visual pathway
21
The striate cortex

• Composed of hyper-columns
• Within each are columns of cells tuned to
  features of a particular orientation

22
Summary

• Image formation
• Very early visual processing
• Filling in and perceptual effects
• Colour perception
• Eye-cortex mapping

23
Reading

• Vicki Bruce, Visual Perception, pp1-60
• Neil Carlson, Physiology of Behavior, pp142-157