L3: VSLAM 1 Flashcards

1
Q

What is WIndowed BA?

A

Iteratively refine over the last m number of frames to obtain a more accurate estimate of the local trajectory.

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

❗️❗️❗️What defines VO?

A

Process of incrementally estimating the pose of the camera by
examining the changes that motion induces on the images.

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

What is VSLAM?

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

❗️❗️❗️What is the difference between VO and VSLAM?

A

VO:
1. aims at LOCAL consistency of the trajectory
2. building block of SLAM
3. VO is SLAM before closing the loop!
4. There is drift (“solved” with windowed BA)

VSLAM:
1. aims at GLOBAL consistency of the trajectory
2. uses LC

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

What is the difference between VO and SFM?

A

VO:

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

What different moion estimation exist?

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

What is Loop Closure (LC)?

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

What is Structured for Motion (SFM)?

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

What properties are important when performing VO?

A
  1. Sufficient illumination in the environment
  2. Dominance of static scene over moving objects (Stationary object preferred over e.g. moving cars)
  3. Enough texture to allow apparent motion to be extracted
  4. Sufficient scene overlap between consecutive frames
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Advantages of VO

A

VO > wheel odometry → Not affected by wheel slip

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

Flow chart of VO

A

Image sequence

Feature detection

Feature matching (tracking)

Motion estimation
(2D-2D, 3D-3D, 3D-2D)

Local optimization

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

Why would we use BA and not just VO?

A

Computes camera path incrementally (pose after pose), the errors introduced by each new frame-to-frame motion accumulate over time. Generates drift of the estimated trajectory from the real path.
To keep small as possible BA is needed as it determined the projection error that minimizes it.

WIndowed BA as a solution to VO locally

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

Which two approaches can be used to estimate the relative motion (T_k) between frames?

Under input sequence process

A
  1. Appearance-based → Intensity information of all pixels in both images. Slow, computationally heavy, worse at estimating and dense.
  2. Feature-based → Repeatable features extracted across the images. Faster and more accurate, and sparse.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is 2D-2D?

A
  • Both features are defined in 2D. - Mostly used in monocular VO
  • Minimal-case solution involves 5-point correspondences (Nister).
  • Or you can use 8-point correspondences (Longurt). Uses SVD at the end.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is 3D-3D?

A
  • Both features are specified in 3D
  • Triangulate 3D points
  • Minimal-case solution involves 3 non-collinear correspondences
  • Solution is found by aligning transformation that minimizes 3D-3D distance
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is 3D-2D

A
  • Previous frame in 3D and current frame in 2D
  • Known as PnP problem
  • Minimal-case solution involves 3 correspondences
  • Solution is found by determining the transformation that minimizes reprojection error
17
Q

What affects triangulation uncertainty and how can the uncertainty be reduced?

A
18
Q

What advantages are there to using stereo vision?

A

Stereo vision has an advantage over monocular as it has less drift.
- Through when the distance to the scene is much larger than the baseline for stereo, VO becomes ineffective and you should monocular VO

Windowed BA should always be used for accurate estimate of the trajectory.

Keyframes should be selected carefully to reduce drift.

19
Q

What casues outliers among feature points?

A

Wrong data associations
Wrong measurements

Causes:
- image noise
- occlusions
- blur
- change in view and illumination (depending on the feature extractor/descriptor)

20
Q

What is Robust Estimation?

A

To remove outliers so camera motion can be estimated accurately

21
Q

How can outliers be removed from estimation?

A

RANSAC
Estimates fraction of inliers adaptively, iteratively.

22
Q

How can glocal consistency be achieved?

A

After loop closure are detected, use bundle adjustment to optimize the camera path!!!