european space agency - matching sparse networks of...
TRANSCRIPT
Group of Robotics and Cognitive Systems http://robotics.pme.duth.gr/
Democritus University of Thrace Department of Production and Management Engineering, Greece
European Space Agency, European Space Research and Technology Centre (ESTEC)
Network/Partnering Initiative (NPI)
Matching Sparse Networks of Semantic ROIs Among Rover and Orbital Imagery
Evangelos Boukas, Antonios Gasteratos, Gianfranco Visentin
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 2
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 3
Motivation
• Advanced space missions require increased autonomy. • Localization is a sine qua non for Space Exploratory Rovers. • Is relative localization enough?
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 4
Motivation
• Advanced space missions require increased autonomy. • Localization is a sine qua non for Space Exploratory Rovers. • Is relative localization enough? • Mars Sample Return (MSR) mission:
• Fetch sample within a very narrow time window. • Even more with multiple “drop-off” of samples as a possibility for
Mars2020.
• ESA NPI: “Methods to Refine the Self-Localization of Planetary Rovers Using Orbital Imaging”.
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 5
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 6
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 7
European Space Agency Network/Partnering Initiative (NPI) • European Space Agency co-funds and supports PhD and post-doc
research • Main objectives:
• Strengthen the links among ESA, Universities, Research institutes and Industry.
• Apply recent non-space technology to space programs.
• Provides: • Co-funding. • Access to ESTEC laboratories (6-12 months). • Technical support. • Networking via ESA links.
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 8
European Space Agency Network/Partnering Initiative (NPI) • Laboratory of Robotics and Automation, School of Engineering,
Democritus University of Thrace. • “Methods to Refine the Self-Localization of Planetary Rovers
Using Orbital Imaging”. • Improve the global localization of Space Rovers. • Urge from previous ESA activities on localization and rover
integration: • SPARTAN project – VO for Rovers on FPGA
• Real Data. • Multiple scenarios.
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 9
European Space Agency Network/Partnering Initiative (NPI) • Key features:
• Extraction of commonly observed Regions of Interest (ROIs) on both orbital and rover imagery
• Opportunistic approaches to refine the localization • Integration of multiple localization techniques:
• Locally on the rover • Globally on Georeferenced images
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 10
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 11
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 12
Related Work
• OSU Mapping and GIS Laboratory: • Global Localization and daily rover traverses for MER using DEM generated
from satellite imagery. • Tie points on rover-orbital network, Bundle adjustment to find position. • The tie points were selected manually.
• JPL (L. Mathies, et al., Isairas 1997, Tokyo): • Combining lander, rover and descent imagery to improve localization near the
rover landing site. • Skyline Based Approach (“VIPER”, Stein and Medioni, 1992, 1995):
• Extract skylines from rover • Create possible skylines on DEMs • Match the rover skylines to the orbital ones
• LIDAR based (Furgale et al., 2010) • Create peaks on LIDAR scans • Match from DEM peaks
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 13
Related Work
• Terrain Matching (Van Pham et al., ASTRA 2013): • Create local DEMs. • Match using Particle Filters to Global DEMs. (Also Hwangbo et al. (2009)).
• Boulder based VO (Lourakis and Hourdakis, ASTRA 2015): • Utilize boulders from robot stereo and orbital imagery to improve the
visual odometry.
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 14
Mars-like Real Dataset
• Atacama Seeker Dataset (Woods et al., Astra 2013) • Mars like scenery:
• Large Rocks. • Outcrops (mostly salars). • Ground (sand).
• UAV: • Georefernced, Orthorectified Images (spatial resolution up to 0.1m). • Digital Elevation Models (DEM).
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 15
Orthorectified Images
Digital Elevation Model
Mars-like Real Dataset
• Atacama Seeker Dataset 2012 (Woods et al. ASTRA 2013) • Robovolc based rover, max 1𝑚𝑚
𝑠𝑠 up to 7 hours.
• More than 5km (in a day ) • Sensors
• Stereo Camera. • Inertial Measurement Unit (IMU). • Wheel Odometry. • DGPS
• Features • Rocky and smooth terrain. • Direct sunlight (at some parts). • Great instantaneous alterations (mostly around the roll axis).
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 16
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 17
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 18
Global Localization System
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 19
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
Detection on Orbital Imagery
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 20
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
Detection on Orbital Imagery
• Detection of prominent shapes (inc. blob-like, ellipse-like)
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 21
∂2I∂x∂x
∂2I∂x∂y
∂2I∂y∂x
∂2I∂y∂y
H(x, y)=
• Hessian Analysis: • Second order partial derivatives along image directions. • Hessian eigenvalues define the principal curvature. • Extreme eigenvalues of Hessian correspond to protruding and well defined shapes in the
image .
• Local Entropy: • Weighted Entropy • Gaussian coefficient w(i) to make low differentiations negligible • Only extreme values are considered as blob candidates.
Orbital Image
Hessian Analysis
Entropy Response
Adaptive Thresholding for Rock
Detection
Adaptive Thresholding for
Outcrop Detection
Rock Candidates
Outcrop Candidates
Detection on Orbital Imagery
• Methods that detect different and complementary regions • Logical OR operation • Binary image filling • Filtering based on the size of ROIs
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 22
An example of the detection employing the mixture of Hessian and
Entropy
An example of the detection employing solely the Hessian analysis
Classification on Orbital Imagery
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 23
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
Classification on Orbital Imagery
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 24
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
OFFLINE PROCEDURE
ROI Global Network
Classification: Feature Space
• Intensity Values: • RGB. • HSV. • Grayscale.
• Local Entropy. • Gabor Features:
• σ, standard deviation of the 2D Gaussian. • θ, orientation of the sinusoidal. • φ, phase offset.
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 25
Classification: Feature Generation
• Feature vector: N-Dimensional vector • Data matrix: MxN matrix, M number of samples • “Raw” Feature vectors size:
• 20px by 20px ROIs. • Intensity, 400 values. • Entropy, 400 values. • Gabor, 28800 values.
• Principal Component Analysis (PCA) • Linear mapping to a subspace. • 32800 dimensional vector 119 dimensional vector, 99% of information.
5/19/2015 Advanced Space Technologies in Robotics and Automation
(ASTRA 2015) 26
Classification: k-NN
• k Nearest Neighborhoods vote • Simple • Competes (some cases) SVM and Perceptor based methods • Only one parameter to setup
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 27
An example “Outcrop vs Ground" classication result.
An example “Rock vs Ground" classication result.
Global ROI network (GN)
Relative Localization
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 28
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
OFFLINE PROCEDURE
ROI Global Network
Relative Localization
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 29
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
Relative Localization
• Visual Odometry: • 3D Reconstruction. • Feature Matching. • Filtering. • EPnP.
• IMU & VO fussion: (loosely coupled)
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 30
Left Image (t-1)
Right Image (t-1)
Left Image (t)
Right Image (t)
Features: Detection, Description
Features: matching
Local 3D Map Disparity Calculation 3D Reconstruction
Local 3D Map Disparity Calculation 3D Reconstruction
3D Reconstruction
Matched 3D Points
Matched 2D Points
3-point RANSAC 3D to 3D
Motion Estimation
Inliers
Best Transform
Efficient PnP 3D to 2D
Pose Estimation
Visual Odometry Motion Estimation
Inertial Measurement Unit (IMU)
Extended Kalman Filter (EKF)
Rover Relative Localization
Relative Localization: 3D Map Building • Disparity calculation from stereo pairs • 3D points are reconstructed for every consequent frame. • Intensity info from the left image of the stereo pair.
_
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 31
Relative Localization: Results
Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 32
• Tested on 64000 stereo frames, without dropping any between. Most relative long range implementations are • either managing the data to be utilized by dropping some frames with low
movement as in Konolige’s Work or • realigning the relative visual odometry with the groundtruth for the first 50
meters of several traverse sections (with varying lengths of 300 to 600 m) as in Lambert’s work.
• 64000 stereo frames, a traverse of more than 3080m • the algorithm is executed without any user intervention or data selection.
• The respective IMU measurements at each frame are utilized as they offer a great correction to the relative localization system.
[1] Konolige, K., Agrawal, M. and Sola, J. Large-scale visual odometry for rough terrain. Springer 2011. [2] Lambert, A., Furgale, P., Barfoot, T.D. and Enright, J. Field testing of visual odometry aided by a sun sensor and inclinometer. Wiley 2012.
Detection on Rover Imagery
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 33
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
Detection on Rover Imagery
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 34
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
Detection on Rover Imagery
• Hessian Analysis • Entropy • Horizon Detection • 3D reconstruction
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 35
Left Stereo Image
Right Stereo Image
Disparity Calculation
3D Reconstruction
Hessian Analysis
Entropy Response
Horizon Detection
Appearance Adaptive Thresholding for Rock
Detection
Appearance Adaptive Thresholding for
Outcrop Detection
Geometrical Thresholding for Rock
Detection
Geometrical Thresholding for
Outcrop Detection
Rock Candidates
Outcrop Candidates
Example rover image containing
rocks. Hessian. Entropy
Example rover image containing
outcrops. Hessian Entropy
Horizon Rock Detection Mask Horizon Outcrop
Detection Mask
Classification on Rover Imagery
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 36
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
Classification on Rover Imagery
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 37
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
Classification on Rover Imagery
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 38
Classification on Rover Imagery
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 39
Local Network (LN)
ROI Matching
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 40
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
ROI Matching
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 41
Detection of ROIs
Classification & Outlier Rejection
ROI Local Network
Relative Localization (VO & IMU)
Inertial Measurements
Rover Stereo Pair
ROI Local Network Update
ROI Sub-Network Match
Rover Global Localization
ONBOARD PROCEDURE
Detection of ROIs
Classification & Outlier Rejection
Orbital Images
ROI Global Network
OFFLINE PROCEDURE
ROI Matching
• Data-Aligned Rigidity-Constrained Exhaustive Search (DARCES) • Create constellations (triangles) of control points on the LN. • Calculate all hypotheses of triangle matches among LN and GN. • Prune the number of valid hypotheses with constraints:
• Edges length • Orientation • Semantic information (Outcrop, Rock)
• Select the affine transformation that best fits the LN-GN
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 42
ROI Matching: Results
• The final error of the localization is 38.46 m after a route of 3076.76 m in an area of approximately 6 km2.
• Most importantly the rover is globally localized!
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 43
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 44
Outline
• Motivation • ESA Network/Partnering Initiative (NPI) • Related Work • Global Localization System • Repeatability of Matching • Discussion - Conclusions
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 45
Repeatability of Matching
• Create simulated traverses: • Based on the GN • Simulate the system’s detection
capabilities (~87%) • Simulate the localization error
(+1%,-1%)
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 46
• 174 ROIs on GN • >58000 simulated trajectories • 99.3% of correct matching. The algorithm is robust (given the assumptions of ROI plethora).
Conclusions
• Achievements: • Global Localization System • Rover ability to autonomously detect ROIs • Tested the system for robustness
• Next steps: • Improvements in:
• Detection of candidate ROI • Machine Learning (GP, Deep Learning for classification) • Infuse our system with a Bayesian Recursive framework
• Building a rover for long range navigation
• No method is panacea
5/19/2015 Advanced Space Technologies in Robotics and Automation (ASTRA 2015) 47
Group of Robotics and Cognitive Systems http://robotics.pme.duth.gr/
Democritus University of Thrace Department of Production and Management Engineering, Greece
European Space Agency, European Space Research and Technology Centre (ESTEC)
Network/Partnering Initiative (NPI)
Matching Sparse Networks of Semantic ROIs Among Rover and Orbital Imagery
Evangelos Boukas, Antonios Gasteratos, Gianfranco Visentin