Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

KCL computer vision > w7 gemini > Flashcards

w7 gemini Flashcards

1
Q

What is the main goal of stereo vision?

A

To infer depth from two or more images taken from different viewpoints.

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

What are the two main sub-problems in stereo vision?

A

Correspondence and Reconstruction.

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

What is the correspondence problem in stereo vision?

A

The challenge of finding matching points in the left and right images that correspond to the same 3D point in the scene.

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

What are some of the stereo constraints that can be used to solve the correspondence problem?

A

Epipolar constraint
maximum disparity constraint
continuity constraint
uniqueness constraint
ordering constraint.

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

Explain the epipolar constraint for coplanar cameras.

A

For coplanar cameras, corresponding points will lie on the same row (the ‘epipolar’ line) in both images.

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

What is the maximum disparity constraint?

A

The length of the search region for a corresponding point is limited by the maximum expected disparity.

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

Explain the continuity constraint in the context of stereo vision.

A

Neighbouring points in an image are likely to correspond to points at similar depths.

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

What is the uniqueness constraint in stereo vision?

A

A location in one image should ideally match only a single location in the other image.

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

What is the ordering constraint in stereo vision?

A

Matching points along corresponding epipolar lines should appear in the same order in both images.

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

What are the basic requirements for solving the correspondence problem?

A

Most scene points must be visible in both images, and corresponding image regions should appear similar.

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

Under what conditions do the basic requirements for correspondence tend to hold?

A

When the distance of the 3D point from the cameras is much larger than the baseline (z&raquo_space; B).

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

What are the two main approaches to solving the stereo correspondence problem?

A

Correlation-based methods and Feature-based methods.

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

What is the output of correlation-based methods for correspondence?

A

Dense disparity maps.

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

What is the output of feature-based methods for correspondence?

A

Sparse disparity maps.

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

What are the characteristics of a simple case of stereo vision with coplanar cameras?

A

Image planes of cameras are coplanar, focal lengths are equal, optical centers are at the same height, and optical axes are parallel.

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

How is disparity calculated for coplanar cameras?

A

d = x’L - x’R

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What is the relationship between depth and disparity?

A

Depth is inversely proportional to disparity.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What is a disparity map?

A

A field of disparity vectors for a pair of stereo images.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What is the significance of the baseline in a stereo vision system?

A

It is the distance between the optical centers of the two cameras.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What are the characteristics of a complex case of stereo vision with non-coplanar cameras?

A

Cameras are not aligned such that their image planes are coplanar.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What is measured instead of distance for disparity in non-coplanar cameras?

A

Angles.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What is the formula for disparity in non-coplanar cameras using angles?

A

Disparity = αL - αR

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What is the horopter?

A

A curve in 3D space where objects project to corresponding points on the retina with zero disparity.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

What are some other cues to depth besides stereo vision?

A

Binocular, Oculomotor, Monocular, and Motion cues.

25
Q

What are the oculomotor cues to depth?

A

Accommodation and Convergence.

26
Q

Explain accommodation as a depth cue.

A

The shape of the lens in the eye adjusts to focus on objects at different depths.

27
Q

Explain convergence as a depth cue.

A

The angle of rotation of the eyes needed to fixate on an object at a certain depth.

28
Q

What are some monocular cues to depth?

A

Interposition, Size familiarity, Texture gradients, Linear perspective, Aerial perspective, and Shading.

29
Q

Explain interposition as a depth cue.

A

When one object blocks the view of another, the occluding object is perceived as being closer.

30
Q

Explain size familiarity as a depth cue.

A

Knowing the typical size of an object helps in judging its distance.

31
Q

Explain texture gradients as a depth cue.

A

For uniformly textured surfaces, the texture elements appear smaller and more closely spaced with increasing distance.

32
Q

Explain linear perspective as a depth cue.

A

Parallel lines appear to converge as they recede into the distance.

33
Q

Explain aerial perspective as a depth cue.

A

Distant objects appear fuzzier and have lower luminance contrast and color saturation.

34
Q

Explain shading as a depth cue.

A

The distribution of light and shadow on objects provides information about their shape and depth.

35
Q

What are some motion-induced cues to depth?

A

Motion parallax, Optic Flow, Accretion and deletion, and Structure from motion.

36
Q

Explain motion parallax as a depth cue.

A

The apparent speed and direction of motion of objects differ based on their distance.

37
Q

Explain optic flow as a depth cue.

A

As an observer moves, the pattern of apparent motion of objects provides information about relative depth.

38
Q

Explain accretion and deletion as motion-induced depth cues.

A

As an observer moves, parts of a background object may become covered or uncovered by a foreground object.

39
Q

Explain structure from motion (kinetic depth) as a depth cue.

A

The perception of a 3D structure can be derived from the changing 2D projections of the object.

40
Q

What is epipolar geometry?

A

The geometry of the situation involving two cameras looking at the same scene.

41
Q

What is an epipole?

A

The projection of the optical center of one camera onto the image plane of the other camera.

42
Q

What are epipolar lines?

A

Lines in one image that correspond to a point in the other image.

43
Q

What are conjugated epipolar lines?

A

The epipolar lines generated by the same 3D point on the left and right image planes.

44
Q

What is the Epipolar Constraint in the context of general (non-coplanar) cameras?

A

Corresponding points must lie on conjugated epipolar lines.

45
Q

What is rectification in the context of stereo vision?

A

A transformation applied to the stereo image pair to make the epipolar lines parallel to the image rows.

46
Q

What knowledge is required for triangulation and rectification in stereo vision?

A

Knowledge of intrinsic and extrinsic camera parameters.

47
Q

Why is recovery of depth information important in computer vision?

A

For controlling movement, 3D reconstruction, and object recognition.

48
Q

What is the difference between coplanar and non-coplanar cameras in terms of epipolar lines after rectification?

A

After rectification, epipolar lines in both cases become horizontal.

49
Q

What is a limitation of stereo vision related to the field of view?

A

A stereo pair of cameras can only find depth for locations within the common field of view.

50
Q

How does the length of the baseline affect the common field of view and depth error in coplanar stereo vision?

A

A short baseline leads to a larger common field of view but a larger depth error.

51
Q

What is the convergence angle in non-coplanar stereo vision?

A

The angle between the optical axes of the two cameras when they are fixated on a point.

52
Q

How does the location of the horopter depend on the vergence angle?

A

The location of the horopter changes based on the convergence angle.

53
Q

What is the significance of retinal disparity in human vision?

A

Some cortical neurons are tuned to retinal disparity.

54
Q

What are ‘crossed’ and ‘uncrossed’ disparities in human vision?

A

Points nearer than the horopter create ‘crossed’ disparities, while points more distant create ‘uncrossed’ disparities.

55
Q

What are some limitations of the uniqueness constraint?

A

It doesn’t hold when surfaces lie along a line-of-sight for one camera.

56
Q

What are some limitations of the ordering constraint?

A

It doesn’t hold when objects have different depths, causing occlusions.

57
Q

Why is correspondence fundamentally ambiguous?

A

Because for a given point in one image, there can be multiple potential matching points in the other image.

58
Q

What are two reasons why some points in each image may have no corresponding points in the other image?

A

Due to occlusion or because the cameras might have different fields of view.

KCL computer vision (12 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions