76
Robot Navigation Using a Single Camera Ludovico Orlando Russo MSc in Mechatronic Engineering Politecnico di Torino Supervisors: Basilio Bona, Luca Carlone, Matteo Matteucci Telecom Italia October 15 th 2013 Ludovico Orlando Russo MSc in Mechatronic Engineering October 15 th 2013 1/13

Master Thesis Ludovico Russo - Presentation

Embed Size (px)

Citation preview

Page 1: Master Thesis Ludovico Russo - Presentation

Robot Navigation Using a Single Camera

Ludovico Orlando Russo

MSc in Mechatronic EngineeringPolitecnico di Torino

Supervisors: Basilio Bona, Luca Carlone, Matteo MatteucciTelecom Italia

October 15th 2013

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 1/13

Page 2: Master Thesis Ludovico Russo - Presentation

Outline

1 IntroductionRobot NavigationSLAMThe Chosen Approach

2 Mono-SLAMThe Mono-SLAM AlgorithmThe developed solutionResults

3 Conclusion and Future Works

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 2/13

Page 3: Master Thesis Ludovico Russo - Presentation

Introduction Robot Navigation

Navigation

LocalizationMapping

SLAM

Robot Navigation

Capabilities anautonomous robot musthave

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 3/13

Page 4: Master Thesis Ludovico Russo - Presentation

Introduction Robot Navigation

Navigation

LocalizationMapping

SLAM

LocalizationAbility of a robot toestablish its position in aknown environment

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 3/13

Page 5: Master Thesis Ludovico Russo - Presentation

Introduction Robot Navigation

Navigation

LocalizationMapping

SLAM

Mapping

Ability to build arepresentation of anunknown environment

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 3/13

Page 6: Master Thesis Ludovico Russo - Presentation

Introduction Robot Navigation

Navigation

LocalizationMapping

SLAM

SLAMSimultaneous Localizationand Mapping

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 3/13

Page 7: Master Thesis Ludovico Russo - Presentation

Introduction SLAM

SLAMClassic

Approaches

VisualApproaches

Dense

Sparse

Semantic

Classic Approaches

Based on Laser ScannersSensors

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 4/13

Page 8: Master Thesis Ludovico Russo - Presentation

Introduction SLAM

SLAMClassic

Approaches

VisualApproaches

Dense

Sparse

Semantic

Visual Approaches

Based on visual systemsMonocular cameraDepth-map system

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 4/13

Page 9: Master Thesis Ludovico Russo - Presentation

Introduction SLAM

SLAMClassic

Approaches

VisualApproaches

Dense

Sparse

Semantic

Dense Approaches

Build up a dense map! Robustness% Computational power

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 4/13

Page 10: Master Thesis Ludovico Russo - Presentation

Introduction SLAM

SLAMClassic

Approaches

VisualApproaches

Dense

Sparse

Semantic

Sparse Approaches

Build up a sparse map% Robustness! Computational power

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 4/13

Page 11: Master Thesis Ludovico Russo - Presentation

Introduction SLAM

SLAMClassic

Approaches

VisualApproaches

Dense

Sparse

Semantic

Semantic Approaches

Build up a semantic map! Robustness! Computational power% Very complex

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 4/13

Page 12: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Mono-SLAM MonocularCamera

EKFFast

Real Time

GeneralPurposeHW

Sparse Probabilistic VisualSLAM approach [1]

Andrew J Davison et al.“MonoSLAM: Real-timesingle camera SLAM”.In: Pattern Analysisand Machine Intelligence,IEEE Transactions on 29.6(2007)

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 5/13

Page 13: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Mono-SLAM MonocularCamera

EKFFast

Real Time

GeneralPurposeHW

Based on a monocularcamera

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 5/13

Page 14: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Mono-SLAM MonocularCamera

EKFFast

Real Time

GeneralPurposeHW

Built upon the ExtendedKalman Filter

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 5/13

Page 15: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Mono-SLAM MonocularCamera

EKFFast

Real Time

GeneralPurposeHW

Developed to be fast

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 5/13

Page 16: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Mono-SLAM MonocularCamera

EKFFast

Real Time

GeneralPurposeHW

Able to meet real timeconstraints

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 5/13

Page 17: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Mono-SLAM MonocularCamera

EKFFast

Real Time

GeneralPurposeHW

Does not need dedicatedhardware

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 5/13

Page 18: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

State of the Mono-SLAMµk =

(xT

k f T1 . . . f T

m)T ← Complete state of the EKF

xk =(rTk qT

k vTk wT

k)T ← 3D camera pose and velocities

f i ← represents each point in the map

yx

z

Ck

f i

y

x

z

W

(rk qk

)

yx

z

Ck+1

(vk wk

)∆t

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 6/13

Page 19: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Features Matching

Using information from EKFPatch matching algorithm1-Point RANSAC outlier rejection algorithm

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 7/13

Page 20: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Features Matching

Using information from EKFPatch matching algorithm1-Point RANSAC outlier rejection algorithm

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 7/13

Page 21: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Features Matching

Using information from EKFPatch matching algorithm1-Point RANSAC outlier rejection algorithm

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 7/13

Page 22: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Features Matching

Using information from EKFPatch matching algorithm1-Point RANSAC outlier rejection algorithm

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 7/13

Page 23: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Features Matching

Using information from EKFPatch matching algorithm1-Point RANSAC outlier rejection algorithm

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 7/13

Page 24: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Features Matching

Using information from EKFPatch matching algorithm1-Point RANSAC outlier rejection algorithm

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 7/13

Page 25: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Features Matching

Using information from EKFPatch matching algorithm1-Point RANSAC outlier rejection algorithm

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 7/13

Page 26: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The Mono-SLAM Algorithm

Features Matching

Using information from EKFPatch matching algorithm1-Point RANSAC outlier rejection algorithm

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 7/13

Page 27: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 8/13

Page 28: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Contribution ROS Imple-mentation

Motion blurhandling

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 9/13

Page 29: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Contribution ROS Imple-mentation

Motion blurhandling

Camera

Camera Topic

frameMono-SLAM

Mono-SLAM Topics

Map

Path

Camera Pose

Elaborated Frame

Rviz

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 9/13

Page 30: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Contribution ROS Imple-mentation

Motion blurhandling

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 9/13

Page 31: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Contribution ROS Imple-mentation

Motion blurhandling

[2] L. O. Russo, G. Airò Farulla, M. Indaco, Rolfo D. Rosa S., and B.Bona. “Blurring prediction in Monocular SLAM”. In: InternationalDesign and Test Symposium, IEEE Conference (2013).

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 9/13

Page 32: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 33: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 34: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 35: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 36: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 37: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 38: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 39: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 40: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 41: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 42: Master Thesis Ludovico Russo - Presentation

Mono-SLAM The developed solution

Featuresmatching

UpdateEKF Step

PredictionEKF Step

MeasurementsPrediction

BlurPredictionz−1

z−1

z−1

Patcheshandler

Capture andpreprocessCamera

Sk+1Sk

yk|k−1

µk|k

Σk|k

µk|k+1

Σk|k+1

P ′k+1|kP ′k|k−1

fk

yk+1|k

−yk ek

Pk

µk|k

Mono-SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 10/13

Page 43: Master Thesis Ludovico Russo - Presentation

Mono-SLAM Results

10m

Starting point

Ground TruthMono-SLAM

10m

Starting point

Starting point50m

20m

Starting point

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 11/13

Page 44: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Open Issues

RobustnessScale DriftLarge Scale Navigation

Future Works

ImprovementsLoop ClosingMulti Camera SLAMMulti Robot SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 12/13

Page 45: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Open Issues

RobustnessScale DriftLarge Scale Navigation

Future Works

ImprovementsLoop ClosingMulti Camera SLAMMulti Robot SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 12/13

Page 46: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Open Issues

RobustnessScale DriftLarge Scale Navigation

Future Works

ImprovementsLoop ClosingMulti Camera SLAMMulti Robot SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 12/13

Page 47: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Open Issues

RobustnessScale DriftLarge Scale Navigation

Future Works

ImprovementsLoop ClosingMulti Camera SLAMMulti Robot SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 12/13

Page 48: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Open Issues

RobustnessScale DriftLarge Scale Navigation

Future Works

ImprovementsLoop ClosingMulti Camera SLAMMulti Robot SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 12/13

Page 49: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Open Issues

RobustnessScale DriftLarge Scale Navigation

Future Works

ImprovementsLoop ClosingMulti Camera SLAMMulti Robot SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 12/13

Page 50: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Open Issues

RobustnessScale DriftLarge Scale Navigation

Future Works

ImprovementsLoop ClosingMulti Camera SLAMMulti Robot SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 12/13

Page 51: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Open Issues

RobustnessScale DriftLarge Scale Navigation

Future Works

ImprovementsLoop ClosingMulti Camera SLAMMulti Robot SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 12/13

Page 52: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Open Issues

RobustnessScale DriftLarge Scale Navigation

Future Works

ImprovementsLoop ClosingMulti Camera SLAMMulti Robot SLAM

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 12/13

Page 53: Master Thesis Ludovico Russo - Presentation

Conclusion and Future Works

Thank you!

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 13/13

Page 54: Master Thesis Ludovico Russo - Presentation

Real Time

15 20 25 30 35 40 45 50 55 60 65 70

20

40

60

number of features

t[m

s]

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 14/13

Page 55: Master Thesis Ludovico Russo - Presentation

Blur Handling

2 4 6 8 10 12 14 16 18

1

1.1

1.2

1.3

low speed medium speed high speed

vp [pixel/frame]

r

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 15/13

Page 56: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem

The 3D Reconstruction ProblemExtrapolate 3D information from a set of 2D images

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 16/13

Page 57: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Stereo Triangulation

Stereo Triangulation

Computing 3D information from a stereo system

V2

V1

pb

f

h

h = bf∆v

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 17/13

Page 58: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Stereo Triangulation

Stereo Triangulation: Step 1

Select a point on the first image

V2

V1

pb

f

h

h = bf∆v

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 17/13

Page 59: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Stereo Triangulation

Stereo Triangulation: Step 2

Match the selected point with the second image

V2

V1

pb

f

h

h = bf∆v

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 17/13

Page 60: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Stereo Triangulation

Stereo Triangulation: Step 3

Triangulate

V2

V1

pb

f

h

h = bf∆v

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 17/13

Page 61: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Stereo Triangulation

Stereo Triangulation: Uncertainty Propagation

Uncertainty on depth h increases when disparity ∆v decreases, i.e.when depth increases:

δh = bf δv1

∆v2 =δvbf

h2

δh

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 18/13

Page 62: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Stereo Triangulation

Stereo Triangulation: Uncertainty Propagation

Uncertainty on depth h increases when disparity ∆v decreases, i.e.when depth increases:

δh = bf δv1

∆v2 =δvbf

h2

δh

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 18/13

Page 63: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Stereo Triangulation

Stereo Triangulation: Uncertainty Propagation

Uncertainty on depth h increases when disparity ∆v decreases, i.e.when depth increases:

δh = bf δv1

∆v2 =δvbf

h2

δh

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 18/13

Page 64: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Structure from MotionComputing 3D information on map and camera path from a video

3 v3y3

y2

2v2

1 v1y1

p

y

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 19/13

Page 65: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Structure from Motion: Step 1

Select a point on the first image

3 v3y3

y2

2v2

1 v1y1

p

y

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 19/13

Page 66: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Structure from Motion: Step 2

Match the selected point with all the others image

3 v3y3

y2

2v2

1 v1y1

p

y

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 19/13

Page 67: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Structure from Motion: Step 3

Compute poses of each camera and triangulate the map

3 v3y3

2v2y2

1 v1y1

p

y

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 19/13

Page 68: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Structure from Motion: Scale LossSfM and similar approach are not able to evaluate the scale of theenvironment

p

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 20/13

Page 69: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Structure from Motion: Scale LossSfM and similar approach are not able to evaluate the scale of theenvironment

p

p∗

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 20/13

Page 70: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Structure from Motion: Scale LossSfM and similar approach are not able to evaluate the scale of theenvironment

p

DimensionlessreformulationEquivalentdimensionlessproblem based onangles

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 20/13

Page 71: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Features Codings: Euclidian Representation

y =(x y z

)T

Simple (3 componets)Unable to represents features with low parallaxPoor Linearity

yx

z

C

p

y

r0

1ρµ(θ, φ)

y

x

z

W

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 21/13

Page 72: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Features Codings: Inverse Depth Representation

y =(rT0 θ φ ρ

)T

More complex (6 components)Able to represents features with low parallax (at infinity)Good linearity

yx

z

C

p

y

r0

1ρµ(θ, φ)

y

x

z

W

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 21/13

Page 73: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Features Codings InverseDepth Init

Points atInfinity

EucledianWellknowndepth

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 22/13

Page 74: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Features Codings InverseDepth Init

Points atInfinity

EucledianWellknowndepth

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 22/13

Page 75: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Features Codings InverseDepth Init

Points atInfinity

EucledianWellknowndepth

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 22/13

Page 76: Master Thesis Ludovico Russo - Presentation

The 3D Reconstruction Problem Structure from Motion

Features Codings InverseDepth Init

Points atInfinity

EucledianWellknowndepth

Ludovico Orlando Russo MSc in Mechatronic Engineering October 15th 2013 22/13