VISION IN PEOPLE AND COMPUTERS

unclesamnorweiganΤεχνίτη Νοημοσύνη και Ρομποτική

18 Οκτ 2013 (πριν από 4 χρόνια και 2 μήνες)

125 εμφανίσεις

VISION IN PEOPLE AND COMPUTERS

Carlo Tomasi, Computer Science

Human Vision

Computer Vision?

Human Vision

?

Seeing is Interpretation

Seeing is Interpretation

Seeing is Interpretation

Seeing is Recognition

Giuseppe Arcimboldo, 1526
-
1593

Computer Vision

frog, mushroom

reconstruction

recognition

Reconstruction: Stereo

Triangulation is Easy

Correspondence is Hard

?

It Can be Done (More or Less)

Face Recognition

Recognition: Face Space

Recognition: Face Space

Hardware


HDTV video camera:


10M pixels, uniform


30
-
60 frames per second


20 Mbits per second (compressed)


Variable field of view up to 1/3 of a sphere


Human eye:


7M cones in the fovea, 120M rods


1.2M axons in the optic nerve


0.6Mbits per second (compressed)


1/3 of a sphere field of view


28
arcsec

resolution (finger at 30 m)

Hardware


$1M buys you this from Dell:


10
12

operations per second


10
12

bytes of memory


10
15

bytes of disk space


10
12

bytes per second of communication


[speed of light 3x10
8

m/s]


One human brain gets you this:


10
12

neurons


10
15

synapses (connections)


[speed of action potential 10
0
-
10
2

m/s]

Comparing Apples and Oranges


David Marr, 1945
-
1980, Cambridge (UK), MIT


The levels:


Computational:
What


Algorithmic:
How


Mechanical:
Wherewith


Computational goals are the same


Algorithms can be similar


Brains are essentially parallel


Computers are essentially sequential


Mechanical substrate is different

Paying the Bills