Perception 3 Flashcards

(39 cards)

1
Q

One reason why it’s difficult to design a perceiving machine

A

Visual input provides ambiguous information about the 3d structure of the world

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Another reason why it’s difficult to design a perceiving machine

A

Image complexity makes it increasingly tricky for computers to organize the visual scene into distinct objects

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

How do we perceive depth

A

Humans make use of a variety of sources of image information to infer depth in a visual scene

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Relative height is a ___ cue

A

Monocular

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Monocular cues

A

Work with one eye

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Relative size is a ____ cue

A

Monocular

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Occlusion is a ____ cue

A

Monocular

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Linear perspective is a ____ cue

A

Monocular

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Texture gradient is a _____ cue

A

Monocular

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Motion parallax is a ____ cue

A

Monocular

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Shading is a ____ cue

A

Monocular

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Binocular cue

A

Requires both eyes

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Disparity is a ____ cue

A

Binocular

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Relative size and height

A

Objects below the horizon and have their bases higher are typically perceived as more distant, and two objects of equal size the more distant one will take up less of your field view

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

We need ______ ______ about relative sizes of objects when judging distance

A

Prior knowledge

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Occlusion

A

Closer objects will block further away ones

17
Q

Parallel lines extending away from observer

A

Converge in the distance

18
Q

Texture elements get smaller and

A

More dense with distance

19
Q

Foreshortening

A

Circles become ovals; occurs when surface is tilted away

20
Q

Motion parallax

A

As we move more distant objects will glide past us more slowly than nearer objects

21
Q

Shadows create perception of

22
Q

Stereoscopic vision

A

Our eyes each receive a slightly different image

23
Q

Binocular disparity

A

Since we have two slightly different images from our each of our eyes, there is a difference in image location

24
Q

Size of disparity depends on

A

Object’s depth

25
Objects closer than the horopter have _____ disparities
Crossed
26
Objects further than the horopter have _____ disparities
Uncrossed
27
Structuralism
Proposed that perceptions are simply the sum of atoms of sensation
28
Gestalt school argued that
The whole form is greater than the sum of its parts
29
Illusory contours
Some images evoke the perception of edges in locations where there isn’t change in luminance or color
30
Illusory contours are difficult to explain via
The structuralist approach
31
Gestalt principles
Proximity, similarity, common fate, good continuation, closure, symmetry
32
Proximity
Things that are close together group together
33
Similarity
Things that are similar group together
34
Common fate
Things that move together group together
35
Good continuation
Group elements to form smoothly continuing lines rather than abrupt or sharp angles
36
Closure
Group elements to form complete figures, even if incomplete
37
Symmetry
Elements more likely to be formed into groups that are balanced or symmetrical
38
Gestalt principles don’t hold up because
They’re too vague, no evidence
39
Gestalt principles seem correct such as
Perceptual objects aren’t just sum of their parts and hold across a lot of images