SlideShare ist ein Scribd-Unternehmen logo
1 von 23
Downloaden Sie, um offline zu lesen
Technische Universität München
Master thesis : Mono- and stereo-camera
SLAM with ranging aid
Chiraz Nafouki Supervisors: Dr. Gabriele Giorgi
chiraz.nafouki@tum.de gabriele.giorgi@tum.de
M.Sc. Chen Zhu
chen.zhu@tum.de
Mid-term presentation
26/07/2016
Technische Universität München
Outline
1. Motivation
2. Problem Formulation
3. Method: Bundle Adjustment (BA)
4. Related work: Monocular SLAM with ranging aid
5. BA for stereo SLAM with ranging aid
6. Work flow
7. Experimental results
Technische Universität München
3
Motivation
Why visual-SLAM with ranging aid?
● Drift in SLAM due to cumulative error (stereo and monocular).
● Scale factor ambiguity in monocular SLAM.
● Possible solution: Integrate ranging information.
Scale ambiguity in monocular SLAM Drift in stereo SLAM
3
Technische Universität München
Problem Formulation
Static base
station
(reference)
Rover
● Problem: Given an initial trajectory estimation (𝑥𝑖′, 𝑦𝑖′, 𝜃𝑖′) in navigation frame 𝑁 and
ranging measurements 𝜌𝑖, correct the estimated trajectory using bundle adjustment.
● Two-dimensional simplification (planar motion).
𝜌1
𝜌2
𝜃1′
𝑥′
𝑦′
𝑥′
𝑦′
World frame
(W)
Navigation
frame (N)
𝜃2′
𝑥′
𝑥′
4
Technische Universität München
Problem Formulation
Static base
station
(reference)
Rover
● Absolute attitude (𝛼0) ambiguity: Trajectory can be rotated around the base station with
ranging measurements invariance.
● Assumption: Rover starts at 𝑟0 1,0 .
𝛼0
𝛼0
𝛼0
𝑥′
𝑥′
𝑥′
𝑦′
𝑦′
𝑦′
5
𝑟0
Technische Universität München
Projection of world coordinates into image
coordinates
𝑢 =
𝑥
𝑦
1
= 𝜋 𝑿, R, 𝐭 = P𝐗 = K[R 𝒕]𝐗 =
−𝑓 0 𝑃𝑥
0 −𝑓 𝑃𝑦
0 0 1
[R 𝒕]
𝑋
𝑌
𝑍
1
𝑢: ℎ𝑜𝑚𝑜𝑔𝑒𝑛𝑒𝑜𝑢𝑠 𝑖𝑚𝑎𝑔𝑒 𝑐𝑜𝑜𝑟𝑑𝑖𝑛𝑎𝑡𝑒𝑠
𝑿: 3𝐷 𝑝𝑜𝑖𝑛𝑡 𝑐𝑜𝑜𝑟𝑑𝑖𝑛𝑎𝑡𝑒𝑠
𝑅, 𝒕 ∶ 𝑟𝑜𝑡𝑎𝑡𝑖𝑜𝑛 𝑎𝑛𝑑 𝑡𝑟𝑎𝑛𝑠𝑙𝑎𝑡𝑖𝑜𝑛
𝜋: 𝑝𝑟𝑜𝑗𝑒𝑐𝑡𝑖𝑜𝑛 𝑓𝑢𝑛𝑐𝑡𝑖𝑜𝑛
𝑃: 𝑝𝑟𝑜𝑗𝑒𝑐𝑡𝑖𝑜𝑛 𝑚𝑎𝑡𝑟𝑖𝑥
𝐾: 𝑐𝑎𝑚𝑒𝑟𝑎 𝑚𝑎𝑡𝑟𝑖𝑥
𝑓: 𝑓𝑜𝑐𝑎𝑙 𝑙𝑒𝑛𝑔𝑡ℎ
(𝑃𝑥 , 𝑃𝑦): 𝑝𝑟𝑖𝑛𝑐𝑖𝑝𝑎𝑙 𝑝𝑜𝑖𝑛𝑡 𝑐𝑜𝑜𝑟𝑑𝑖𝑛𝑎𝑡𝑒𝑠
6
Technische Universität München
7
Method : Bundle Adjustment (BA)
with Ck
(N)
: camera position at frame k in navigation frame N
𝜃 𝑘
(𝑁)
: 𝑟𝑒𝑙𝑎𝑡𝑖𝑣𝑒 𝑎𝑡𝑡𝑖𝑡𝑢𝑑𝑒 𝑖𝑛 (𝑁)
Xi
(N)
: coordinates of ith 3D feature in (N)
ui
(k)
: measured image projection of Xi
(N)
into kth
camera frame
π ∶ projection function
n ∶ total number of features, K: total number of frames.
ɳ𝑖,𝑘: coefficient of the covariance matrix of image projections
𝑎𝑟𝑔𝑚𝑖𝑛
𝑋𝑖
(𝑁)
, 𝐶 𝑘
(𝑁)
, 𝜃 𝑘
(𝑁)
𝑐𝑜𝑠𝑡 𝑓𝑢𝑛𝑐𝑡𝑖𝑜𝑛
𝑘=0
𝐾
𝑖=1
𝑛
ɳ𝑖,𝑘 𝑢𝑖
(𝑘)
− 𝜋(𝑋𝑖
𝑁
, 𝐶 𝑘
𝑁
, 𝜃 𝑘
(𝑁)
)
2
𝑥′
● BA aims at refining camera pose and 3D feature coordinates.
● Minimize the reprojection error:
● Non-linear least-squares problem solved using Levenberg-Marquardt (LM) algorithm.
𝐶1
𝑁
𝐶2
𝑁
y′
7
𝜃1
(𝑁)
𝜃2
(𝑁)
Technische Universität München
8
Related Work : Scale estimation in monocular
SLAM with ranging measurements
𝑟𝑘 = 𝐶 𝑘
𝑊
= 𝑓 𝐶 𝑘
𝑁
, 𝑠, 𝛼0, 𝑟0 = 𝑓𝑘 𝛏 , 𝑤𝑖𝑡ℎ 𝛏 = 𝑠, 𝛼0, 𝑟0
● Solving this LS problem gives us 𝐶 𝑘
(𝑁)
only up to a scale 𝑠.
● Approach: Use ranging measurements to find 𝑠.
● The distance 𝑟𝑘 between the rover and the base station at frame 𝑘 :
● Solve the non-linear minimization problem using LM algorithm:
𝑎𝑟𝑔𝑚𝑖𝑛
𝜉
k=0
𝐾
𝑤 𝑘(𝜌 𝑘 − 𝑓𝑘 𝝃 )2
Find minimizer 𝝃 and therefore scale 𝑠.
𝑖=1
𝑛
ɳ𝑖,𝑘 𝑢𝑖
(𝑘)
− 𝜋(𝑋𝑖
𝑁
, 𝐶 𝑘
𝑁
, 𝜃 𝑘
(𝑁)
)
2
𝑎𝑟𝑔𝑚𝑖𝑛
𝐶 𝑘
(𝑁)
, 𝜃 𝑘
(𝑁)
𝑟1
𝑟2
𝛼0
𝑟0 𝑥′
y′
8
Technische Universität München
9
𝑎𝑟𝑔𝑚𝑖𝑛
𝜉
k=0
𝐾
𝑤 𝑘(𝜌 𝑘 − 𝑓𝑘 𝝃 )2
Disadvantages of this approach :
● Local optimization of the reprojection error
● Ranging measurements are exploited for scale correction
𝑎𝑟𝑔𝑚𝑖𝑛
𝐶 𝑘
(𝑁)
, 𝜃 𝑘
(𝑁) 𝑖=1
𝑛
ɳ𝑖,𝑘 𝑢𝑖
(𝑘)
− 𝜋(𝑋𝑖
𝑁
, 𝐶 𝑘
𝑁
, 𝜃 𝑘
(𝑁)
)
2
9
Related Work : Scale estimation in monocular
SLAM with ranging measurements
with 𝑓𝑘 𝝃 = 𝐶 𝑘
𝑊
, 𝛏 = 𝑠, 𝛼0, 𝑟0
Technische Universität München
Stereo case: BA with ranging measuremets
● No scale ambiguity.
● Ranging measurements can be used to reduce the trajectory drift.
● Approach: include the ranging measurements into the cost function of BA.
𝑘=0
𝐾
𝑖=1
𝑛
ɳ𝑖,𝑘 𝑢𝑖
(𝑘)
− 𝜋(𝑋𝑖
𝑊
, 𝐶 𝑘
𝑊
, 𝜃 𝑘
(𝑊)
)
2
+ 𝑤 𝑘(𝜌 𝑘 − 𝐶 𝑘
𝑊
)2
𝑐𝑜𝑠𝑡 𝑓𝑢𝑛𝑐𝑡𝑖𝑜𝑛
𝑎𝑟𝑔𝑚𝑖𝑛
𝑋𝑖
(w)
, 𝐶 𝑘
(W)
, 𝜃 𝑘
(𝑊)
10
𝐶1
𝑊
𝐶2
𝑊
𝑥′
y′
𝐶0
𝑊
Technische Universität München
Initial camera
frame positon
3D feature
Corrected camera
frame position
Drift correction using ranging measurements
● Advantage: no need for loop closure to reduce the drift
● Loop closure: Recognizing previously observed landmarks
● In absence of loop closure, drift due to accumulation of errors
Stereo case: BA with ranging aid
11
Technische Universität München
12
Work flow
Feature detection
& extraction
Motion tracking
(Visual Odometry)
Bundle Adjustment
Feature
Matching
& triangulation
Key frame
selection
Database
Left Image
Range measurements
Right Image
Image
undistortion &
rectification
Key frames
Estimated
Trajectory
3D points &
their projectionsMap
Corrected trajectory
and map
12
Technische Universität München
Image undistortion and rectification
• Compute the affine transformation that reduces radial and tangential distortions.
• Compute the rotations such that corresponding epipolar lines are aligned
horizontally (epipolar constraint).
13
Technische Universität München
14
Feature detection & extraction
Feature Matching
● Feature detector uses a corner detector (Harris detector)
● Feature descriptor uses response to a Sobel filter.
● Matching is based on the sum of absolute differences (SAD).
● Matching is done between the left and right images and between two consecutive frames.
Feature matching between left and right camera images using LIBVISO2 library
14
Technische Universität München
Triangulation
• Feature points are projected into 3D via triangulation:
15
𝑋 = 𝑥 − 𝑃𝑥 ∗
𝑏
𝑑
𝑌 = y − 𝑃𝑦 ∗
𝑏
𝑑
𝑍 = 𝑓 ∗
𝑏
𝑑
where 𝑥, 𝑦 ∶ 2𝐷 𝑐𝑜𝑜𝑟𝑑𝑖𝑛𝑎𝑡𝑒𝑠 𝑖𝑛 𝑡ℎ𝑒 𝑙𝑒𝑓𝑡 𝑖𝑚𝑎𝑔𝑒
𝑃𝑥, 𝑃𝑦 : 𝑖𝑠 𝑡ℎ𝑒 𝑝𝑟𝑖𝑛𝑐𝑖𝑝𝑎𝑙 𝑝𝑜𝑖𝑛𝑡 𝑜𝑓 𝑡ℎ𝑒 𝑙𝑒𝑓𝑡 𝑐𝑎𝑚𝑒𝑟𝑎
𝑓 ∶ 𝑖𝑠 𝑡ℎ𝑒 𝑓𝑜𝑐𝑎𝑙 𝑙𝑒𝑛𝑔𝑡ℎ
𝑏 ∶ 𝑖𝑠 𝑡ℎ𝑒 𝑏𝑎𝑠𝑒𝑙𝑖𝑛𝑒
𝑑 ∶ 𝑖𝑠 𝑡ℎ𝑒 𝑑𝑖𝑠𝑝𝑎𝑟𝑖𝑡𝑦
Technische Universität München
Motion tracking (Visual Odometry)
• Use of LIBVISO2: C++ Library for Visual Odometry.
• Camera motion (R, t) is estimated by minimizing the sum of reprojection error:
• Solve through Gauss-Newton optimization method.
• RANSAC is applied for more robustness.
𝑖=1
𝑛
𝑢𝑖
(l)
− 𝜋(𝑙)(𝑋𝑖 ; 𝑅, 𝐭)
2
+ 𝑢𝑖
(r)
− 𝜋(𝑟)(𝑋𝑖 ; 𝑅, 𝐭)
2
16
Technische Universität München
17
Ranging measurements
For real experiments, use a checkboard as fixed reference and measure the distance to it:
● Detect checkboard (using OpenCV)
● Calculate distance 𝑑 to checkboard (m):
17
with 𝑓: 𝑓𝑜𝑐𝑎𝑙 𝑙𝑒𝑛𝑔𝑡ℎ 𝑚
𝐿: 𝑔𝑟𝑖𝑑 𝑠𝑖𝑧𝑒 𝑖𝑛 𝑚𝑒𝑡𝑟𝑖𝑐 𝑚
𝑙: 𝑔𝑟𝑖𝑑 𝑠𝑖𝑧𝑒 𝑖𝑛 𝑖𝑚𝑎𝑔𝑒 𝑝𝑖𝑥𝑒𝑙𝑠
𝒅 =
𝒇 ∗ 𝑳
𝒍
Technische Universität München
18
Ranging measurements
0
1
2
3
4
5
6
7
8
9
0 50 100 150 200
Error(cm)
True distance to the checkboard (cm)
• Ranging measurement error increases with distance to
checkboard.
• Problem of checkboard detection.
Technische Universität München
19
Experimental Set up
● VI-Sensor: Visual-Inertial Sensor
● Calibrated stereo camera
● Resolution: 752 × 480
● Frame rate: 20 fps
● Interface the Sensor From ROS
19
Technische Universität München
Experimental Results
Results using VI-Sensor
• BA for 3168 3D points and 100 frames
• Computation time 43 seconds
• 50 iterations for LM algorithm
• Reduction of the reprojection error from 6007,84 to 192,894
• Implementation of work flow (without ranging measurement and without keyframes
selection)
• Implementation of Bundle adjustment using the Sparse Bundle Adjustment (sba)
C++ package
• Estimation of the initial and final total reprojection error
Technische Universität München
21
Experimental Results
Results on Karlsruhe dataset (KITTI dataset)
• Stereo sequence recorded from a moving vehicle
• Calibration parameters and ground Truth provided
• BA for 52672 3D points and 250 frames
• Computation time 111,43 seconds
• 150 iterations for LM algorithm
• Reduction of the reprojection error from 8093,9 to 21,24
21
Technische Universität München
22
Next?
● Integration of ranging measurements and keyframes selection in BA
● Mapping
● Compare with ground truth and other approaches
Optional:
● Try other feature detectors/descriptors
● Loop closure detection
● Report and final presentation: end of October
22
Technische Universität München
23
References
23
The Design and Implementation of a Generic Sparse Bundle Adjustment Software
Package Based on the Levenberg-Marquardt Algorithm
M.I. A. Lourakis and A.A. Argyros
StereoScan: Dense 3d Reconstruction in Real-time
Andreas Geiger, Julius Ziegler and Christoph Stiller
Visual Odometry Part I: The First 30 Years and Fundamentals
Davide Scaramuzza and Friedrich Fraundorfer
Real-time Monocular SLAM: Why Filter?
Hauke Strasdat, J. M. M. Montiel and Andrew J. Davison

Weitere ähnliche Inhalte

Was ist angesagt?

IRJET- Study on the Feature of Cavitation Bubbles in Hydraulic Valve by using...
IRJET- Study on the Feature of Cavitation Bubbles in Hydraulic Valve by using...IRJET- Study on the Feature of Cavitation Bubbles in Hydraulic Valve by using...
IRJET- Study on the Feature of Cavitation Bubbles in Hydraulic Valve by using...IRJET Journal
 
New geometric interpretation and analytic solution for quadrilateral reconstr...
New geometric interpretation and analytic solution for quadrilateral reconstr...New geometric interpretation and analytic solution for quadrilateral reconstr...
New geometric interpretation and analytic solution for quadrilateral reconstr...Joo-Haeng Lee
 
REVIEW OF LANE DETECTION AND TRACKING ALGORITHMS IN ADVANCED DRIVER ASSISTANC...
REVIEW OF LANE DETECTION AND TRACKING ALGORITHMS IN ADVANCED DRIVER ASSISTANC...REVIEW OF LANE DETECTION AND TRACKING ALGORITHMS IN ADVANCED DRIVER ASSISTANC...
REVIEW OF LANE DETECTION AND TRACKING ALGORITHMS IN ADVANCED DRIVER ASSISTANC...ijcsit
 
Build Your Own 3D Scanner: Course Notes
Build Your Own 3D Scanner: Course NotesBuild Your Own 3D Scanner: Course Notes
Build Your Own 3D Scanner: Course NotesDouglas Lanman
 
Photogrammetry - areaotriangulation
Photogrammetry - areaotriangulationPhotogrammetry - areaotriangulation
Photogrammetry - areaotriangulationjayan_sri
 
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHMA ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHMcsandit
 
Visual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environmentsVisual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environmentsNAVER Engineering
 
A genetic algorithm aimed at optimising seismic retrofitting of existing RC f...
A genetic algorithm aimed at optimising seismic retrofitting of existing RC f...A genetic algorithm aimed at optimising seismic retrofitting of existing RC f...
A genetic algorithm aimed at optimising seismic retrofitting of existing RC f...openseesdays
 
An automatic algorithm for object recognition and detection based on asift ke...
An automatic algorithm for object recognition and detection based on asift ke...An automatic algorithm for object recognition and detection based on asift ke...
An automatic algorithm for object recognition and detection based on asift ke...Kunal Kishor Nirala
 
An accurate retrieval through R-MAC+ descriptors for landmark recognition
An accurate retrieval through R-MAC+ descriptors for landmark recognitionAn accurate retrieval through R-MAC+ descriptors for landmark recognition
An accurate retrieval through R-MAC+ descriptors for landmark recognitionFederico Magliani
 
Touya et al_issdq_presentation
Touya et al_issdq_presentationTouya et al_issdq_presentation
Touya et al_issdq_presentationGuillaume Touya
 
ScaleMaster 2.0: a ScaleMaster extension to monitor automatic multi-scales ge...
ScaleMaster 2.0: a ScaleMaster extension to monitor automatic multi-scales ge...ScaleMaster 2.0: a ScaleMaster extension to monitor automatic multi-scales ge...
ScaleMaster 2.0: a ScaleMaster extension to monitor automatic multi-scales ge...Guillaume Touya
 
Vehicle detection in Aerial Images
Vehicle detection in Aerial ImagesVehicle detection in Aerial Images
Vehicle detection in Aerial ImagesKoshy Geoji
 
Vision Based Traffic Surveillance System
Vision Based Traffic Surveillance SystemVision Based Traffic Surveillance System
Vision Based Traffic Surveillance Systemmaheshwaraneee
 
426 Lecture5: AR Registration
426 Lecture5: AR Registration426 Lecture5: AR Registration
426 Lecture5: AR RegistrationMark Billinghurst
 
AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...
AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...
AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...aciijournal
 

Was ist angesagt? (20)

CAMERA
CAMERACAMERA
CAMERA
 
IRJET- Study on the Feature of Cavitation Bubbles in Hydraulic Valve by using...
IRJET- Study on the Feature of Cavitation Bubbles in Hydraulic Valve by using...IRJET- Study on the Feature of Cavitation Bubbles in Hydraulic Valve by using...
IRJET- Study on the Feature of Cavitation Bubbles in Hydraulic Valve by using...
 
New geometric interpretation and analytic solution for quadrilateral reconstr...
New geometric interpretation and analytic solution for quadrilateral reconstr...New geometric interpretation and analytic solution for quadrilateral reconstr...
New geometric interpretation and analytic solution for quadrilateral reconstr...
 
REVIEW OF LANE DETECTION AND TRACKING ALGORITHMS IN ADVANCED DRIVER ASSISTANC...
REVIEW OF LANE DETECTION AND TRACKING ALGORITHMS IN ADVANCED DRIVER ASSISTANC...REVIEW OF LANE DETECTION AND TRACKING ALGORITHMS IN ADVANCED DRIVER ASSISTANC...
REVIEW OF LANE DETECTION AND TRACKING ALGORITHMS IN ADVANCED DRIVER ASSISTANC...
 
Build Your Own 3D Scanner: Course Notes
Build Your Own 3D Scanner: Course NotesBuild Your Own 3D Scanner: Course Notes
Build Your Own 3D Scanner: Course Notes
 
Photogrammetry - areaotriangulation
Photogrammetry - areaotriangulationPhotogrammetry - areaotriangulation
Photogrammetry - areaotriangulation
 
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHMA ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
 
Visual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environmentsVisual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environments
 
A genetic algorithm aimed at optimising seismic retrofitting of existing RC f...
A genetic algorithm aimed at optimising seismic retrofitting of existing RC f...A genetic algorithm aimed at optimising seismic retrofitting of existing RC f...
A genetic algorithm aimed at optimising seismic retrofitting of existing RC f...
 
06466595
0646659506466595
06466595
 
An automatic algorithm for object recognition and detection based on asift ke...
An automatic algorithm for object recognition and detection based on asift ke...An automatic algorithm for object recognition and detection based on asift ke...
An automatic algorithm for object recognition and detection based on asift ke...
 
A real-time system for vehicle detection with shadow removal and vehicle clas...
A real-time system for vehicle detection with shadow removal and vehicle clas...A real-time system for vehicle detection with shadow removal and vehicle clas...
A real-time system for vehicle detection with shadow removal and vehicle clas...
 
An accurate retrieval through R-MAC+ descriptors for landmark recognition
An accurate retrieval through R-MAC+ descriptors for landmark recognitionAn accurate retrieval through R-MAC+ descriptors for landmark recognition
An accurate retrieval through R-MAC+ descriptors for landmark recognition
 
Touya et al_issdq_presentation
Touya et al_issdq_presentationTouya et al_issdq_presentation
Touya et al_issdq_presentation
 
ScaleMaster 2.0: a ScaleMaster extension to monitor automatic multi-scales ge...
ScaleMaster 2.0: a ScaleMaster extension to monitor automatic multi-scales ge...ScaleMaster 2.0: a ScaleMaster extension to monitor automatic multi-scales ge...
ScaleMaster 2.0: a ScaleMaster extension to monitor automatic multi-scales ge...
 
Vehicle detection in Aerial Images
Vehicle detection in Aerial ImagesVehicle detection in Aerial Images
Vehicle detection in Aerial Images
 
Vision Based Traffic Surveillance System
Vision Based Traffic Surveillance SystemVision Based Traffic Surveillance System
Vision Based Traffic Surveillance System
 
13
1313
13
 
426 Lecture5: AR Registration
426 Lecture5: AR Registration426 Lecture5: AR Registration
426 Lecture5: AR Registration
 
AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...
AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...
AN EFFICIENT SYSTEM FOR FORWARD COLLISION AVOIDANCE USING LOW COST CAMERA & E...
 

Andere mochten auch

Does running damage your knees
Does running damage your kneesDoes running damage your knees
Does running damage your kneesHospital Khoj
 
5 reasons why digital health is the next top performer in emerging countries
5 reasons why digital health is the next top performer in emerging countries5 reasons why digital health is the next top performer in emerging countries
5 reasons why digital health is the next top performer in emerging countriesMEDx eHealthCenter
 
El archipiélago de Cabo Verde
El archipiélago de Cabo VerdeEl archipiélago de Cabo Verde
El archipiélago de Cabo VerdeRobin Hood
 
Mobile application development for android with phonegap
Mobile application development for android with phonegapMobile application development for android with phonegap
Mobile application development for android with phonegapSayed Ahmed
 
Orientaciones para la planeación didáctica en los servicios de EE
Orientaciones para la planeación didáctica en los servicios de EEOrientaciones para la planeación didáctica en los servicios de EE
Orientaciones para la planeación didáctica en los servicios de EEAngélica Villanueva
 
Exploring The Implementation Of Quality Teaching And Learning Of Ordinary Lev...
Exploring The Implementation Of Quality Teaching And Learning Of Ordinary Lev...Exploring The Implementation Of Quality Teaching And Learning Of Ordinary Lev...
Exploring The Implementation Of Quality Teaching And Learning Of Ordinary Lev...iosrjce
 
Manual primeros auxilios
Manual primeros auxiliosManual primeros auxilios
Manual primeros auxiliosCarlos Rs
 
Tics y Enfermería
Tics y EnfermeríaTics y Enfermería
Tics y EnfermeríaAlmardo
 
Rick's Keynote for ConnectedPlus (@CPLUS_TO)
Rick's Keynote for ConnectedPlus (@CPLUS_TO) Rick's Keynote for ConnectedPlus (@CPLUS_TO)
Rick's Keynote for ConnectedPlus (@CPLUS_TO) Rick Huijbregts
 
Cours les instument d'urbanisme le permis et certificats
Cours les instument d'urbanisme le permis et certificatsCours les instument d'urbanisme le permis et certificats
Cours les instument d'urbanisme le permis et certificatsArchi Guelma
 
Vía venosa periféricas.
Vía venosa periféricas.Vía venosa periféricas.
Vía venosa periféricas.informaticacra
 
Conférence sur la livraison collaborative- World Class Logistics
Conférence sur la livraison collaborative- World Class LogisticsConférence sur la livraison collaborative- World Class Logistics
Conférence sur la livraison collaborative- World Class LogisticsLogicités
 

Andere mochten auch (17)

Does running damage your knees
Does running damage your kneesDoes running damage your knees
Does running damage your knees
 
Búsqueda en google chrome
Búsqueda en google chromeBúsqueda en google chrome
Búsqueda en google chrome
 
kjirstin_looklet_2016
kjirstin_looklet_2016kjirstin_looklet_2016
kjirstin_looklet_2016
 
5 reasons why digital health is the next top performer in emerging countries
5 reasons why digital health is the next top performer in emerging countries5 reasons why digital health is the next top performer in emerging countries
5 reasons why digital health is the next top performer in emerging countries
 
Diapositivas van van
Diapositivas van vanDiapositivas van van
Diapositivas van van
 
El archipiélago de Cabo Verde
El archipiélago de Cabo VerdeEl archipiélago de Cabo Verde
El archipiélago de Cabo Verde
 
My Certificate
My CertificateMy Certificate
My Certificate
 
Mobile application development for android with phonegap
Mobile application development for android with phonegapMobile application development for android with phonegap
Mobile application development for android with phonegap
 
Orientaciones para la planeación didáctica en los servicios de EE
Orientaciones para la planeación didáctica en los servicios de EEOrientaciones para la planeación didáctica en los servicios de EE
Orientaciones para la planeación didáctica en los servicios de EE
 
Exploring The Implementation Of Quality Teaching And Learning Of Ordinary Lev...
Exploring The Implementation Of Quality Teaching And Learning Of Ordinary Lev...Exploring The Implementation Of Quality Teaching And Learning Of Ordinary Lev...
Exploring The Implementation Of Quality Teaching And Learning Of Ordinary Lev...
 
Manual primeros auxilios
Manual primeros auxiliosManual primeros auxilios
Manual primeros auxilios
 
Tics y Enfermería
Tics y EnfermeríaTics y Enfermería
Tics y Enfermería
 
Rick's Keynote for ConnectedPlus (@CPLUS_TO)
Rick's Keynote for ConnectedPlus (@CPLUS_TO) Rick's Keynote for ConnectedPlus (@CPLUS_TO)
Rick's Keynote for ConnectedPlus (@CPLUS_TO)
 
Cours les instument d'urbanisme le permis et certificats
Cours les instument d'urbanisme le permis et certificatsCours les instument d'urbanisme le permis et certificats
Cours les instument d'urbanisme le permis et certificats
 
Sondaje vesical
Sondaje vesicalSondaje vesical
Sondaje vesical
 
Vía venosa periféricas.
Vía venosa periféricas.Vía venosa periféricas.
Vía venosa periféricas.
 
Conférence sur la livraison collaborative- World Class Logistics
Conférence sur la livraison collaborative- World Class LogisticsConférence sur la livraison collaborative- World Class Logistics
Conférence sur la livraison collaborative- World Class Logistics
 

Ähnlich wie mid_presentation

SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)Reheman Baikejiang
 
Using Generic Image Processing Operations to Detect a Calibration Grid
Using Generic Image Processing Operations to Detect a Calibration GridUsing Generic Image Processing Operations to Detect a Calibration Grid
Using Generic Image Processing Operations to Detect a Calibration GridJan Wedekind
 
Surface generation from point cloud.pdf
Surface generation from point cloud.pdfSurface generation from point cloud.pdf
Surface generation from point cloud.pdfssuserd3982b1
 
ieee nss mic 2016 poster N30-21
ieee nss mic 2016 poster N30-21ieee nss mic 2016 poster N30-21
ieee nss mic 2016 poster N30-21Dae Woon Kim
 
47549379 paper-on-image-processing
47549379 paper-on-image-processing47549379 paper-on-image-processing
47549379 paper-on-image-processingmaisali4
 
Carved visual hulls for image based modeling
Carved visual hulls for image based modelingCarved visual hulls for image based modeling
Carved visual hulls for image based modelingaftab alam
 
Review_of_phase_measuring_deflectometry.pdf
Review_of_phase_measuring_deflectometry.pdfReview_of_phase_measuring_deflectometry.pdf
Review_of_phase_measuring_deflectometry.pdfSevgulDemir
 
Design and optimization of compact freeform lens array for laser beam splitti...
Design and optimization of compact freeform lens array for laser beam splitti...Design and optimization of compact freeform lens array for laser beam splitti...
Design and optimization of compact freeform lens array for laser beam splitti...Milan Maksimovic
 
RAPID PRODUCT DEVELOPMENT seminar
RAPID PRODUCT DEVELOPMENT seminarRAPID PRODUCT DEVELOPMENT seminar
RAPID PRODUCT DEVELOPMENT seminarVijay Mohangekar
 
Final Project Report Nadar
Final Project Report NadarFinal Project Report Nadar
Final Project Report NadarMaher Nadar
 
論文読み会@AIST (Deep Virtual Stereo Odometry [ECCV2018])
論文読み会@AIST (Deep Virtual Stereo Odometry [ECCV2018])論文読み会@AIST (Deep Virtual Stereo Odometry [ECCV2018])
論文読み会@AIST (Deep Virtual Stereo Odometry [ECCV2018])Masaya Kaneko
 
Efficient analytical and hybrid simulations using OpenSees
Efficient analytical and hybrid simulations using OpenSeesEfficient analytical and hybrid simulations using OpenSees
Efficient analytical and hybrid simulations using OpenSeesopenseesdays
 
DTAM: Dense Tracking and Mapping in Real-Time, Robot vision Group
DTAM: Dense Tracking and Mapping in Real-Time, Robot vision GroupDTAM: Dense Tracking and Mapping in Real-Time, Robot vision Group
DTAM: Dense Tracking and Mapping in Real-Time, Robot vision GroupLihang Li
 
Realtime pothole detection system using improved CNN Models
Realtime pothole detection system using improved CNN ModelsRealtime pothole detection system using improved CNN Models
Realtime pothole detection system using improved CNN Modelsnithinsai2992
 
Machine learning for Tomographic Imaging.pdf
Machine learning for Tomographic Imaging.pdfMachine learning for Tomographic Imaging.pdf
Machine learning for Tomographic Imaging.pdfMunir Ahmad
 
Machine learning for Tomographic Imaging.pptx
Machine learning for Tomographic Imaging.pptxMachine learning for Tomographic Imaging.pptx
Machine learning for Tomographic Imaging.pptxMunir Ahmad
 

Ähnlich wie mid_presentation (20)

SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)
 
Using Generic Image Processing Operations to Detect a Calibration Grid
Using Generic Image Processing Operations to Detect a Calibration GridUsing Generic Image Processing Operations to Detect a Calibration Grid
Using Generic Image Processing Operations to Detect a Calibration Grid
 
Surface generation from point cloud.pdf
Surface generation from point cloud.pdfSurface generation from point cloud.pdf
Surface generation from point cloud.pdf
 
crowd counting.pptx
crowd counting.pptxcrowd counting.pptx
crowd counting.pptx
 
ieee nss mic 2016 poster N30-21
ieee nss mic 2016 poster N30-21ieee nss mic 2016 poster N30-21
ieee nss mic 2016 poster N30-21
 
47549379 paper-on-image-processing
47549379 paper-on-image-processing47549379 paper-on-image-processing
47549379 paper-on-image-processing
 
Carved visual hulls for image based modeling
Carved visual hulls for image based modelingCarved visual hulls for image based modeling
Carved visual hulls for image based modeling
 
Review_of_phase_measuring_deflectometry.pdf
Review_of_phase_measuring_deflectometry.pdfReview_of_phase_measuring_deflectometry.pdf
Review_of_phase_measuring_deflectometry.pdf
 
Design and optimization of compact freeform lens array for laser beam splitti...
Design and optimization of compact freeform lens array for laser beam splitti...Design and optimization of compact freeform lens array for laser beam splitti...
Design and optimization of compact freeform lens array for laser beam splitti...
 
RAPID PRODUCT DEVELOPMENT seminar
RAPID PRODUCT DEVELOPMENT seminarRAPID PRODUCT DEVELOPMENT seminar
RAPID PRODUCT DEVELOPMENT seminar
 
3D reconstruction
3D reconstruction3D reconstruction
3D reconstruction
 
Final Project Report Nadar
Final Project Report NadarFinal Project Report Nadar
Final Project Report Nadar
 
論文読み会@AIST (Deep Virtual Stereo Odometry [ECCV2018])
論文読み会@AIST (Deep Virtual Stereo Odometry [ECCV2018])論文読み会@AIST (Deep Virtual Stereo Odometry [ECCV2018])
論文読み会@AIST (Deep Virtual Stereo Odometry [ECCV2018])
 
TUPPC055_Final
TUPPC055_FinalTUPPC055_Final
TUPPC055_Final
 
Inverse problems in medical imaging
Inverse problems in medical imagingInverse problems in medical imaging
Inverse problems in medical imaging
 
Efficient analytical and hybrid simulations using OpenSees
Efficient analytical and hybrid simulations using OpenSeesEfficient analytical and hybrid simulations using OpenSees
Efficient analytical and hybrid simulations using OpenSees
 
DTAM: Dense Tracking and Mapping in Real-Time, Robot vision Group
DTAM: Dense Tracking and Mapping in Real-Time, Robot vision GroupDTAM: Dense Tracking and Mapping in Real-Time, Robot vision Group
DTAM: Dense Tracking and Mapping in Real-Time, Robot vision Group
 
Realtime pothole detection system using improved CNN Models
Realtime pothole detection system using improved CNN ModelsRealtime pothole detection system using improved CNN Models
Realtime pothole detection system using improved CNN Models
 
Machine learning for Tomographic Imaging.pdf
Machine learning for Tomographic Imaging.pdfMachine learning for Tomographic Imaging.pdf
Machine learning for Tomographic Imaging.pdf
 
Machine learning for Tomographic Imaging.pptx
Machine learning for Tomographic Imaging.pptxMachine learning for Tomographic Imaging.pptx
Machine learning for Tomographic Imaging.pptx
 

mid_presentation

  • 1. Technische Universität München Master thesis : Mono- and stereo-camera SLAM with ranging aid Chiraz Nafouki Supervisors: Dr. Gabriele Giorgi chiraz.nafouki@tum.de gabriele.giorgi@tum.de M.Sc. Chen Zhu chen.zhu@tum.de Mid-term presentation 26/07/2016
  • 2. Technische Universität München Outline 1. Motivation 2. Problem Formulation 3. Method: Bundle Adjustment (BA) 4. Related work: Monocular SLAM with ranging aid 5. BA for stereo SLAM with ranging aid 6. Work flow 7. Experimental results
  • 3. Technische Universität München 3 Motivation Why visual-SLAM with ranging aid? ● Drift in SLAM due to cumulative error (stereo and monocular). ● Scale factor ambiguity in monocular SLAM. ● Possible solution: Integrate ranging information. Scale ambiguity in monocular SLAM Drift in stereo SLAM 3
  • 4. Technische Universität München Problem Formulation Static base station (reference) Rover ● Problem: Given an initial trajectory estimation (𝑥𝑖′, 𝑦𝑖′, 𝜃𝑖′) in navigation frame 𝑁 and ranging measurements 𝜌𝑖, correct the estimated trajectory using bundle adjustment. ● Two-dimensional simplification (planar motion). 𝜌1 𝜌2 𝜃1′ 𝑥′ 𝑦′ 𝑥′ 𝑦′ World frame (W) Navigation frame (N) 𝜃2′ 𝑥′ 𝑥′ 4
  • 5. Technische Universität München Problem Formulation Static base station (reference) Rover ● Absolute attitude (𝛼0) ambiguity: Trajectory can be rotated around the base station with ranging measurements invariance. ● Assumption: Rover starts at 𝑟0 1,0 . 𝛼0 𝛼0 𝛼0 𝑥′ 𝑥′ 𝑥′ 𝑦′ 𝑦′ 𝑦′ 5 𝑟0
  • 6. Technische Universität München Projection of world coordinates into image coordinates 𝑢 = 𝑥 𝑦 1 = 𝜋 𝑿, R, 𝐭 = P𝐗 = K[R 𝒕]𝐗 = −𝑓 0 𝑃𝑥 0 −𝑓 𝑃𝑦 0 0 1 [R 𝒕] 𝑋 𝑌 𝑍 1 𝑢: ℎ𝑜𝑚𝑜𝑔𝑒𝑛𝑒𝑜𝑢𝑠 𝑖𝑚𝑎𝑔𝑒 𝑐𝑜𝑜𝑟𝑑𝑖𝑛𝑎𝑡𝑒𝑠 𝑿: 3𝐷 𝑝𝑜𝑖𝑛𝑡 𝑐𝑜𝑜𝑟𝑑𝑖𝑛𝑎𝑡𝑒𝑠 𝑅, 𝒕 ∶ 𝑟𝑜𝑡𝑎𝑡𝑖𝑜𝑛 𝑎𝑛𝑑 𝑡𝑟𝑎𝑛𝑠𝑙𝑎𝑡𝑖𝑜𝑛 𝜋: 𝑝𝑟𝑜𝑗𝑒𝑐𝑡𝑖𝑜𝑛 𝑓𝑢𝑛𝑐𝑡𝑖𝑜𝑛 𝑃: 𝑝𝑟𝑜𝑗𝑒𝑐𝑡𝑖𝑜𝑛 𝑚𝑎𝑡𝑟𝑖𝑥 𝐾: 𝑐𝑎𝑚𝑒𝑟𝑎 𝑚𝑎𝑡𝑟𝑖𝑥 𝑓: 𝑓𝑜𝑐𝑎𝑙 𝑙𝑒𝑛𝑔𝑡ℎ (𝑃𝑥 , 𝑃𝑦): 𝑝𝑟𝑖𝑛𝑐𝑖𝑝𝑎𝑙 𝑝𝑜𝑖𝑛𝑡 𝑐𝑜𝑜𝑟𝑑𝑖𝑛𝑎𝑡𝑒𝑠 6
  • 7. Technische Universität München 7 Method : Bundle Adjustment (BA) with Ck (N) : camera position at frame k in navigation frame N 𝜃 𝑘 (𝑁) : 𝑟𝑒𝑙𝑎𝑡𝑖𝑣𝑒 𝑎𝑡𝑡𝑖𝑡𝑢𝑑𝑒 𝑖𝑛 (𝑁) Xi (N) : coordinates of ith 3D feature in (N) ui (k) : measured image projection of Xi (N) into kth camera frame π ∶ projection function n ∶ total number of features, K: total number of frames. ɳ𝑖,𝑘: coefficient of the covariance matrix of image projections 𝑎𝑟𝑔𝑚𝑖𝑛 𝑋𝑖 (𝑁) , 𝐶 𝑘 (𝑁) , 𝜃 𝑘 (𝑁) 𝑐𝑜𝑠𝑡 𝑓𝑢𝑛𝑐𝑡𝑖𝑜𝑛 𝑘=0 𝐾 𝑖=1 𝑛 ɳ𝑖,𝑘 𝑢𝑖 (𝑘) − 𝜋(𝑋𝑖 𝑁 , 𝐶 𝑘 𝑁 , 𝜃 𝑘 (𝑁) ) 2 𝑥′ ● BA aims at refining camera pose and 3D feature coordinates. ● Minimize the reprojection error: ● Non-linear least-squares problem solved using Levenberg-Marquardt (LM) algorithm. 𝐶1 𝑁 𝐶2 𝑁 y′ 7 𝜃1 (𝑁) 𝜃2 (𝑁)
  • 8. Technische Universität München 8 Related Work : Scale estimation in monocular SLAM with ranging measurements 𝑟𝑘 = 𝐶 𝑘 𝑊 = 𝑓 𝐶 𝑘 𝑁 , 𝑠, 𝛼0, 𝑟0 = 𝑓𝑘 𝛏 , 𝑤𝑖𝑡ℎ 𝛏 = 𝑠, 𝛼0, 𝑟0 ● Solving this LS problem gives us 𝐶 𝑘 (𝑁) only up to a scale 𝑠. ● Approach: Use ranging measurements to find 𝑠. ● The distance 𝑟𝑘 between the rover and the base station at frame 𝑘 : ● Solve the non-linear minimization problem using LM algorithm: 𝑎𝑟𝑔𝑚𝑖𝑛 𝜉 k=0 𝐾 𝑤 𝑘(𝜌 𝑘 − 𝑓𝑘 𝝃 )2 Find minimizer 𝝃 and therefore scale 𝑠. 𝑖=1 𝑛 ɳ𝑖,𝑘 𝑢𝑖 (𝑘) − 𝜋(𝑋𝑖 𝑁 , 𝐶 𝑘 𝑁 , 𝜃 𝑘 (𝑁) ) 2 𝑎𝑟𝑔𝑚𝑖𝑛 𝐶 𝑘 (𝑁) , 𝜃 𝑘 (𝑁) 𝑟1 𝑟2 𝛼0 𝑟0 𝑥′ y′ 8
  • 9. Technische Universität München 9 𝑎𝑟𝑔𝑚𝑖𝑛 𝜉 k=0 𝐾 𝑤 𝑘(𝜌 𝑘 − 𝑓𝑘 𝝃 )2 Disadvantages of this approach : ● Local optimization of the reprojection error ● Ranging measurements are exploited for scale correction 𝑎𝑟𝑔𝑚𝑖𝑛 𝐶 𝑘 (𝑁) , 𝜃 𝑘 (𝑁) 𝑖=1 𝑛 ɳ𝑖,𝑘 𝑢𝑖 (𝑘) − 𝜋(𝑋𝑖 𝑁 , 𝐶 𝑘 𝑁 , 𝜃 𝑘 (𝑁) ) 2 9 Related Work : Scale estimation in monocular SLAM with ranging measurements with 𝑓𝑘 𝝃 = 𝐶 𝑘 𝑊 , 𝛏 = 𝑠, 𝛼0, 𝑟0
  • 10. Technische Universität München Stereo case: BA with ranging measuremets ● No scale ambiguity. ● Ranging measurements can be used to reduce the trajectory drift. ● Approach: include the ranging measurements into the cost function of BA. 𝑘=0 𝐾 𝑖=1 𝑛 ɳ𝑖,𝑘 𝑢𝑖 (𝑘) − 𝜋(𝑋𝑖 𝑊 , 𝐶 𝑘 𝑊 , 𝜃 𝑘 (𝑊) ) 2 + 𝑤 𝑘(𝜌 𝑘 − 𝐶 𝑘 𝑊 )2 𝑐𝑜𝑠𝑡 𝑓𝑢𝑛𝑐𝑡𝑖𝑜𝑛 𝑎𝑟𝑔𝑚𝑖𝑛 𝑋𝑖 (w) , 𝐶 𝑘 (W) , 𝜃 𝑘 (𝑊) 10 𝐶1 𝑊 𝐶2 𝑊 𝑥′ y′ 𝐶0 𝑊
  • 11. Technische Universität München Initial camera frame positon 3D feature Corrected camera frame position Drift correction using ranging measurements ● Advantage: no need for loop closure to reduce the drift ● Loop closure: Recognizing previously observed landmarks ● In absence of loop closure, drift due to accumulation of errors Stereo case: BA with ranging aid 11
  • 12. Technische Universität München 12 Work flow Feature detection & extraction Motion tracking (Visual Odometry) Bundle Adjustment Feature Matching & triangulation Key frame selection Database Left Image Range measurements Right Image Image undistortion & rectification Key frames Estimated Trajectory 3D points & their projectionsMap Corrected trajectory and map 12
  • 13. Technische Universität München Image undistortion and rectification • Compute the affine transformation that reduces radial and tangential distortions. • Compute the rotations such that corresponding epipolar lines are aligned horizontally (epipolar constraint). 13
  • 14. Technische Universität München 14 Feature detection & extraction Feature Matching ● Feature detector uses a corner detector (Harris detector) ● Feature descriptor uses response to a Sobel filter. ● Matching is based on the sum of absolute differences (SAD). ● Matching is done between the left and right images and between two consecutive frames. Feature matching between left and right camera images using LIBVISO2 library 14
  • 15. Technische Universität München Triangulation • Feature points are projected into 3D via triangulation: 15 𝑋 = 𝑥 − 𝑃𝑥 ∗ 𝑏 𝑑 𝑌 = y − 𝑃𝑦 ∗ 𝑏 𝑑 𝑍 = 𝑓 ∗ 𝑏 𝑑 where 𝑥, 𝑦 ∶ 2𝐷 𝑐𝑜𝑜𝑟𝑑𝑖𝑛𝑎𝑡𝑒𝑠 𝑖𝑛 𝑡ℎ𝑒 𝑙𝑒𝑓𝑡 𝑖𝑚𝑎𝑔𝑒 𝑃𝑥, 𝑃𝑦 : 𝑖𝑠 𝑡ℎ𝑒 𝑝𝑟𝑖𝑛𝑐𝑖𝑝𝑎𝑙 𝑝𝑜𝑖𝑛𝑡 𝑜𝑓 𝑡ℎ𝑒 𝑙𝑒𝑓𝑡 𝑐𝑎𝑚𝑒𝑟𝑎 𝑓 ∶ 𝑖𝑠 𝑡ℎ𝑒 𝑓𝑜𝑐𝑎𝑙 𝑙𝑒𝑛𝑔𝑡ℎ 𝑏 ∶ 𝑖𝑠 𝑡ℎ𝑒 𝑏𝑎𝑠𝑒𝑙𝑖𝑛𝑒 𝑑 ∶ 𝑖𝑠 𝑡ℎ𝑒 𝑑𝑖𝑠𝑝𝑎𝑟𝑖𝑡𝑦
  • 16. Technische Universität München Motion tracking (Visual Odometry) • Use of LIBVISO2: C++ Library for Visual Odometry. • Camera motion (R, t) is estimated by minimizing the sum of reprojection error: • Solve through Gauss-Newton optimization method. • RANSAC is applied for more robustness. 𝑖=1 𝑛 𝑢𝑖 (l) − 𝜋(𝑙)(𝑋𝑖 ; 𝑅, 𝐭) 2 + 𝑢𝑖 (r) − 𝜋(𝑟)(𝑋𝑖 ; 𝑅, 𝐭) 2 16
  • 17. Technische Universität München 17 Ranging measurements For real experiments, use a checkboard as fixed reference and measure the distance to it: ● Detect checkboard (using OpenCV) ● Calculate distance 𝑑 to checkboard (m): 17 with 𝑓: 𝑓𝑜𝑐𝑎𝑙 𝑙𝑒𝑛𝑔𝑡ℎ 𝑚 𝐿: 𝑔𝑟𝑖𝑑 𝑠𝑖𝑧𝑒 𝑖𝑛 𝑚𝑒𝑡𝑟𝑖𝑐 𝑚 𝑙: 𝑔𝑟𝑖𝑑 𝑠𝑖𝑧𝑒 𝑖𝑛 𝑖𝑚𝑎𝑔𝑒 𝑝𝑖𝑥𝑒𝑙𝑠 𝒅 = 𝒇 ∗ 𝑳 𝒍
  • 18. Technische Universität München 18 Ranging measurements 0 1 2 3 4 5 6 7 8 9 0 50 100 150 200 Error(cm) True distance to the checkboard (cm) • Ranging measurement error increases with distance to checkboard. • Problem of checkboard detection.
  • 19. Technische Universität München 19 Experimental Set up ● VI-Sensor: Visual-Inertial Sensor ● Calibrated stereo camera ● Resolution: 752 × 480 ● Frame rate: 20 fps ● Interface the Sensor From ROS 19
  • 20. Technische Universität München Experimental Results Results using VI-Sensor • BA for 3168 3D points and 100 frames • Computation time 43 seconds • 50 iterations for LM algorithm • Reduction of the reprojection error from 6007,84 to 192,894 • Implementation of work flow (without ranging measurement and without keyframes selection) • Implementation of Bundle adjustment using the Sparse Bundle Adjustment (sba) C++ package • Estimation of the initial and final total reprojection error
  • 21. Technische Universität München 21 Experimental Results Results on Karlsruhe dataset (KITTI dataset) • Stereo sequence recorded from a moving vehicle • Calibration parameters and ground Truth provided • BA for 52672 3D points and 250 frames • Computation time 111,43 seconds • 150 iterations for LM algorithm • Reduction of the reprojection error from 8093,9 to 21,24 21
  • 22. Technische Universität München 22 Next? ● Integration of ranging measurements and keyframes selection in BA ● Mapping ● Compare with ground truth and other approaches Optional: ● Try other feature detectors/descriptors ● Loop closure detection ● Report and final presentation: end of October 22
  • 23. Technische Universität München 23 References 23 The Design and Implementation of a Generic Sparse Bundle Adjustment Software Package Based on the Levenberg-Marquardt Algorithm M.I. A. Lourakis and A.A. Argyros StereoScan: Dense 3d Reconstruction in Real-time Andreas Geiger, Julius Ziegler and Christoph Stiller Visual Odometry Part I: The First 30 Years and Fundamentals Davide Scaramuzza and Friedrich Fraundorfer Real-time Monocular SLAM: Why Filter? Hauke Strasdat, J. M. M. Montiel and Andrew J. Davison