Brainscape's Knowledge GenomeTM

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


See full index

computer_vision_teorico > 3D Vision > Flashcards

3D Vision Flashcards

1
Q

3D Vision:
Name a difficulty when real world scenarios are projected from 3D to 2D in camera images.

A

Depth estimation

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

What are the main two types for 3D Data Acquisition?

A

Passive and Active range sensing

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

How many types of passive methods are there?

A

4
Shape from:
-stereo;
-motion;
shading;
-focus.

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

What are the pros of shape from stereo?

A
  • Cheap (use cameras)
  • Fast acquisition
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What are the cons of shape from stereo?

A
  • Highly dependant on
    correspondences quality
  • Still challenging
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What are the characteristics of Shape from motion?

A

– Similar to stereovision in many ways
– Successive images might be considered as stereo pairs
– With texture, possible to find correspondences (matching techniques, optical flow…) and find fundamental and
essential matrix.

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

What are the characteristics of shape from shading?

A
  • given a continuous surface, and known illumination: intensity variation in the surfaces depends on its orientation
  • Since most surfaces are not uniform and lighting is difficult to control, normally it is combined with other methods
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is shape from focus?

A
  • objects away from focal point are out of focus;
  • with different images with different focus its possible to extract depth information
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

How many types of Active range sensing are there?

A
  • Structured Light Systems
  • Laser Range Finder – Time of Flight
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

How does Structured Light Techniques are implemented?

A

-Projection of a known pattern
- Acquisition with camera, 3D from pattern deformation in scene.

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

What are the only positive point about Structured Light Techniques?

A

It is very accurate

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

What are the cons of Structured Light Techniques?

A
  • Takes time (often need to scan through an area)
    -Sensitive to environment brightness, usually only
    implemented in dark or indoor areas.
  • Short range
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

When are the Laser Range Finders (LRF) used for?

A

They are used for larger areas (buildings, rooms)

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

How do Laser Range Finders (LRF) work?

A

Working principle:
light pulse time of flight - laser ray in -> reflect on object -> laser ray out
- phase shift: amplitude of frequency modulation - comparison of phases

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

What are the LRF pros?

A
  • independent from external lighting;
  • no need of texture in scene;
    -provide directly 3D measurements
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are the LRF cons?

A

They are:
-expensive;
-large sensors = aquisition more difficult;
-limited spatial resolution;
-no color texture map

17
Q

How do 3D ToF Cameras work?

A

They phase shift principle of emitted and received infrared light to measure depth

18
Q

How could we define the perfomance and cost of Structured Light:

A

It has:
- best depth accuracy | shortest range | require dark environment
- Highest cost

19
Q

How could we define the perfomance and cost of Time of Flight (ToF):

A

-performance is up to hundred meters. depending on emitting
power
- moderate cost

20
Q

How could we define the perfomance and cost Camera Array:

A
  • largest depth error | range depend on baseline (dist. between cameras = usually around 10 m)| require bright environment
  • lowest cost | Development mainly on software side
21
Q

In a nutshell Which perform better in the following categories, Active (Range - TOF) or Passive (camera arrays)?
Cost, Acquisition, Depth error, Texture map, Lighting, Texture relevance and 3D processing

A

Cost, Acquisition, Depth error, Texture map (first 4 categories):
Intensity (camera arrays) perform better - Passive

Lighting, Texture Relevance and 3D Processing (last 3 categories):
Are better performed by Range (TOF) -Active

22
Q

What type does Kinect use?

A

Active - infrared pattern.

23
Q

What composes a Kinect?

A

The kinect has:
- a multi-array mic
- 3D Depth sensors
- RGB camera
- motorized tilt

24
Q

Where can 3D Vision be applied?

A

Robotics:
-Navigation, localization, mapping, avoiding collision
AR / VR:
- sensing real 3D environments and reconstructing them in the virtual world

25
Q

To what the AR / VR Interaction’s devices must respond accurately?

A

To the 3D movement, therefore needing high-performance depth sensor

26
Q

What is a Range image?

A

-It is a rectangular array of numbers that quantifies the distance from the sensor to the surfaces within the field of view.
-It isAlso referred as depth image and easily
transform to cloud of points.

27
Q

How do Ranges differ from intensity to range images?

A

-In intensity images: edges related to intensity changes (due to
geometry or aspect - for example colour or shadow)
-In range images: jump or step edge; roof or crease edge; smooth edge

28
Q

What is Registration?

A

It estimates Rigid Body Transform that minimize the distance
between 2 scans

29
Q

What is the ICP (Iterative Closest Point) and how does it work?

A

It is an algortithm used to perform the registration:
– Find closest point
– Compute transform that minimizes error
– Repeat until ending condition.

30
Q

What are the ICP problems?

A
  • algorithm may fall in local minima
  • typically requires an initial guess
  • may result in many outliers
31
Q

Besides ICP, it can also be done registration from clouds to surfaces: How many of these are there?

A

– Non parametric curves (triangles,…)
– Parametric curves (cylinders, quadrics, …)

32
Q

What are some examples of triangulation algorithms?

A

Delaunay triangulation 2D;
Marching cubes;
Marching triangles;
Ball-pivoting;
Poisson Surface Reconstruction;
Moving least-squares (MLS)

33
Q

How does the Delaunay triangulation work?

A

For a set of 2D points P ensure that none points of the set
is inside the circumcircle of any triangle.

34
Q

What is Zippering?

A
  • remove overlapping portion of meshes
  • clip mesh together
  • remove triangles
35
Q

What is Texture Mapping?

A

Some 3D reconstruction techniques that provide automatically texture like for example
– Shape from …
– Structured Light Techniques

36
Q

Do all kinds of reconstruction techniques provide texture?

A

No.
For example: initial Laser Range Finder does not provide texture

computer_vision_teorico (12 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions