Scalable Fiducial Tag Localization on a 3D Prior Map via Graph-Theoretic Global Tag-Map Registration [IROS2022]

Scalable Fiducial Tag Localization on a 3D Prior Map
Via Graph-Theoretic Global Tag-Map Registration
Kenji Koide, Shuji Oishi, Masashi Yokozuka, and Atsuhiko Banno
National Institute of Advanced Industrial Science and Technology (AIST), Japan
Background
• Map-based visual localization has been attracting much attention
• It is, however, sometimes necessary to rely on visual fiducial tags
(aka visual markers) for initialization and fail-safe
[Oishi, 2020]
Motivation
• Deploying many tags on a 3D prior map is sometimes difficult and tedious
• Tag positions are often measured by hand; large effort and inaccurate results
• We aim to develop an accurate and automatic method to determine tag poses
in the environment
Proposed Method
1. VIO-based Tag-Relative-Pose Estimation
We use an agile camera to observe tags in the environment and
estimate the relative poses between tags via landmark SLAM
2. Global Tag-Map Registration
We then roughly align tags and a prior map by establishing tag-plane
correspondences via graph-theoretic correspondence estimation
3. Estimation Refinement via Direct Camera-Map Alignment
Tag and camera poses are refined by directly aligning agile camera images with
the prior map and re-optimize all variables under all constraints
VIO-based Tag-Relative-Pose Estimation
• We use an agile camera and observe each tag in the environment at least once
• The tag poses in the VIO frame is estimated via landmark SLAM
VIO
(VINS-Mono)
Tag detections
(Apriltags)
Pose graph optimization
Global Tag-Map Registration
• We want to align the estimated tag poses with a prior 3D map without initial guess
• The modality difference makes it difficult to apply image matching…
Prior 3D map (sparse point cloud) Estimated tag poses (visually detected)
Align w/o initial guess
Geometry-based Tag-Plane Matching
• We assume that most tags are placed on a plane in the environment
• We establish tag-plane correspondences to determine the tag-map transformation
Detecting planes in the environment
1. Region growing segmentation
2. RANSAC plane detection
3. Fit oriented BBoxes to plane points
Geometry-based Tag-Plane Matching
• We assume that most tags are placed on a plane in the environment
• We establish tag-plane correspondences to determine the tag-map transformation
Detecting planes in the environment
1. Region growing segmentation
2. RANSAC plane detection
3. Fit oriented BBoxes to plane points
Geometry-based Tag-Plane Matching
• We assume that most tags are placed on a plane in the environment
• We establish tag-plane correspondences to determine the tag-map transformation
Detecting planes in the environment
1. Region growing segmentation
2. RANSAC plane detection
3. Fit oriented BBoxes to plane points
Geometry-based Tag-Plane Matching
• We assume that most tags are placed on a plane in the environment
• We establish tag-plane correspondences to determine the tag-map transformation
Detecting planes in the environment
1. Region growing segmentation
2. RANSAC plane detection
3. Fit oriented BBoxes to plane points
Plane = (center, normal, lengths)
Max-Clique-based Correspondence Estimation
• Tag-Plane Correspondence Consistency Graph
Vertex: tag-plane correspondence hypothesis
Edge: consistency between correspondence hypotheses
ℎ𝑖𝑗 does not contradict ℎ𝑘𝑙 (i.e., they are consistent)
Tag i corresponds to plane j
Tag k corresponds to plane l
ℎ𝑖𝑗
ℎ𝑘𝑙
Max-Clique-based Correspondence Estimation
• Tag-Plane Correspondence Consistency Graph
Vertex: tag-plane correspondence hypothesis
Edge: consistency between correspondence hypotheses
ℎ𝑖𝑗
ℎ𝑘𝑙
Max-Clique-based Correspondence Estimation
• Tag-Plane Correspondence Consistency Graph
Vertex: tag-plane correspondence hypothesis
Edge: consistency between correspondence hypotheses
• Largest subset of hypotheses that are all mutually consistent (i.e., maximum clique)
gives the best explanation for the tag placement in the given map
ℎ𝑖𝑗
ℎ𝑘𝑙
Tag-Plane Correspondence Consistency
• Consistency between tag-plane correspondence hypotheses is determined
based on geometric consistency check
ℎ𝑖𝑗
ℎ𝑘𝑙
Tag i
Tag k
Plane j
Plane l
Tag-Plane Correspondence Consistency
• Consistency between tag-plane correspondence hypotheses is determined
based on geometric consistency check
• We align tag i and plane j and s.t. distance between tag k and plane l
Plane j
Plane l
Tag-Plane Correspondence Consistency
• Consistency between tag-plane correspondence hypotheses is determined
based on geometric consistency check
• We align tag i and plane j and s.t. distance between tag k and plane l
• If normal and translation errors between tag k and plane l are smaller than
threshold, these hypotheses are mutually consistent
Plane j
Plane l
Normal error
Translation error
Example Result
Planes
Tags
• While the consistency graph contains many edges,
the max-clique can be found very efficiently [Rossi, 2015]
Example Result
Planes
Tags
Consistency graph contains
429,735 hypothesis pairs
• While the consistency graph contains many edges,
the max-clique can be found very efficiently [Rossi, 2015]
Example Result
Planes
Tags
Consistency graph contains
429,735 hypothesis pairs
Maximum clique consists of
56 tag-plane correspondences
found in 92 msec
• While the consistency graph contains many edges,
the max-clique can be found very efficiently [Rossi, 2015]
• Given the tag-plane correspondences, we estimate the tag-map transformation
by minimizing normal-to-normal ICP distance [Rusinkiewicz, 2019]
Estimation Refinement
• We refine the tag poses by directly aligning agile camera images with the map
VIO
Tag detections
Pose graph
Direct alignment
Estimation Refinement
• We refine the tag poses by directly aligning agile camera images with the map
• We use the normalized information distance (NID), a mutual information-based
cross modal metric, to maximize the co-occurrence of pixel and map intensity values
• Tag and camera poses are re-optimized under all the constraints
Agile camera image
Map rendered with
optimized camera pose
Evaluation in Simulation
• The method is evaluated on the Replica dataset [Savva, 2019]
Global tag-map registration
: 0.039m / 1.021°
Tag localization accuracy
: 98% success rate
Baseline (FPFH+RANSAC/Teaser) : 26% and 70%
Robustness to outlier tags
Evaluation in Real Environment
• 117 tags were placed in the environment
• Tag poses were estimated in 22 minutes (16 min for VIO recording, 6 min for post processing)
• Average tag pose error: 0.019m and 2.382°
Final estimation result
Thank you for your attention!!
24
Conclusion
• An accurate and scalable method for fiducial tag localization on a 3D prior
environmental map is proposed
• VIO-based tag relative pose estimation via landmark SLAM
• Global tag-map registration based on tag-plane correspondence estimation
via maximum clique finding
• Estimation refinement via NID-based direct camera-map alignment
• The proposed method could localize over 100 tags in 22 minutes
• The average tag localization error was about 2 cm
1 of 25

Recommended

Remote Sensing Field Camp 2016 by
Remote Sensing Field Camp 2016 Remote Sensing Field Camp 2016
Remote Sensing Field Camp 2016 COGS Presentations
395 views67 slides
Final Paper by
Final PaperFinal Paper
Final PaperNicholas Chehade
176 views10 slides
Application of Vision based Techniques for Position Estimation by
Application of Vision based Techniques for Position EstimationApplication of Vision based Techniques for Position Estimation
Application of Vision based Techniques for Position EstimationIRJET Journal
26 views5 slides
Video Stitching using Improved RANSAC and SIFT by
Video Stitching using Improved RANSAC and SIFTVideo Stitching using Improved RANSAC and SIFT
Video Stitching using Improved RANSAC and SIFTIRJET Journal
31 views2 slides
Centre of Geographic Sciences Remote Sensing Field Camp 2015 by
Centre of Geographic Sciences Remote Sensing Field Camp 2015Centre of Geographic Sciences Remote Sensing Field Camp 2015
Centre of Geographic Sciences Remote Sensing Field Camp 2015COGS Presentations
372 views28 slides
Centre Of Geographic Sciences Remote Sensing Field Camp 2015 by
Centre Of Geographic Sciences Remote Sensing Field Camp 2015Centre Of Geographic Sciences Remote Sensing Field Camp 2015
Centre Of Geographic Sciences Remote Sensing Field Camp 2015COGS Presentations
244 views28 slides

More Related Content

Similar to Scalable Fiducial Tag Localization on a 3D Prior Map via Graph-Theoretic Global Tag-Map Registration [IROS2022]

IGARSS presentation WKLEE.pptx by
IGARSS presentation WKLEE.pptxIGARSS presentation WKLEE.pptx
IGARSS presentation WKLEE.pptxgrssieee
125 views33 slides
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields by
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation FieldsCVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation FieldsJun Saito
2.6K views29 slides
EFFECTIVE INTEREST REGION ESTIMATION MODEL TO REPRESENT CORNERS FOR IMAGE by
EFFECTIVE INTEREST REGION ESTIMATION MODEL TO REPRESENT CORNERS FOR IMAGE EFFECTIVE INTEREST REGION ESTIMATION MODEL TO REPRESENT CORNERS FOR IMAGE
EFFECTIVE INTEREST REGION ESTIMATION MODEL TO REPRESENT CORNERS FOR IMAGE sipij
14 views10 slides
Geo referencing by Mashhood Arif by
Geo referencing by Mashhood ArifGeo referencing by Mashhood Arif
Geo referencing by Mashhood ArifKU Leuven
1.7K views14 slides
Graphics by
GraphicsGraphics
GraphicsNidhi Baranwal
165 views21 slides
Lecture 4 image measumrents & refinement by
Lecture 4  image measumrents & refinementLecture 4  image measumrents & refinement
Lecture 4 image measumrents & refinementSarhat Adam
2.1K views21 slides

Similar to Scalable Fiducial Tag Localization on a 3D Prior Map via Graph-Theoretic Global Tag-Map Registration [IROS2022](20)

IGARSS presentation WKLEE.pptx by grssieee
IGARSS presentation WKLEE.pptxIGARSS presentation WKLEE.pptx
IGARSS presentation WKLEE.pptx
grssieee125 views
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields by Jun Saito
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation FieldsCVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields
Jun Saito2.6K views
EFFECTIVE INTEREST REGION ESTIMATION MODEL TO REPRESENT CORNERS FOR IMAGE by sipij
EFFECTIVE INTEREST REGION ESTIMATION MODEL TO REPRESENT CORNERS FOR IMAGE EFFECTIVE INTEREST REGION ESTIMATION MODEL TO REPRESENT CORNERS FOR IMAGE
EFFECTIVE INTEREST REGION ESTIMATION MODEL TO REPRESENT CORNERS FOR IMAGE
sipij14 views
Geo referencing by Mashhood Arif by KU Leuven
Geo referencing by Mashhood ArifGeo referencing by Mashhood Arif
Geo referencing by Mashhood Arif
KU Leuven1.7K views
Lecture 4 image measumrents & refinement by Sarhat Adam
Lecture 4  image measumrents & refinementLecture 4  image measumrents & refinement
Lecture 4 image measumrents & refinement
Sarhat Adam2.1K views
Depth Fusion from RGB and Depth Sensors II by Yu Huang
Depth Fusion from RGB and Depth Sensors IIDepth Fusion from RGB and Depth Sensors II
Depth Fusion from RGB and Depth Sensors II
Yu Huang1.4K views
EXTENDED HYBRID REGION GROWING SEGMENTATION OF POINT CLOUDS WITH DIFFERENT RE... by cscpconf
EXTENDED HYBRID REGION GROWING SEGMENTATION OF POINT CLOUDS WITH DIFFERENT RE...EXTENDED HYBRID REGION GROWING SEGMENTATION OF POINT CLOUDS WITH DIFFERENT RE...
EXTENDED HYBRID REGION GROWING SEGMENTATION OF POINT CLOUDS WITH DIFFERENT RE...
cscpconf129 views
Extended hybrid region growing segmentation of point clouds with different re... by csandit
Extended hybrid region growing segmentation of point clouds with different re...Extended hybrid region growing segmentation of point clouds with different re...
Extended hybrid region growing segmentation of point clouds with different re...
csandit293 views
Remote Sensing: Georeferencing by Kamlesh Kumar
Remote Sensing: GeoreferencingRemote Sensing: Georeferencing
Remote Sensing: Georeferencing
Kamlesh Kumar370 views
Effect of sub classes on the accuracy of the classified image by iaemedu
Effect of sub classes on the accuracy of the classified imageEffect of sub classes on the accuracy of the classified image
Effect of sub classes on the accuracy of the classified image
iaemedu502 views
Augmented reality session 4 by NirsandhG
Augmented reality session 4Augmented reality session 4
Augmented reality session 4
NirsandhG59 views
Placing Images with Refined Language Models and Similarity Search with PCA-re... by Symeon Papadopoulos
Placing Images with Refined Language Models and Similarity Search with PCA-re...Placing Images with Refined Language Models and Similarity Search with PCA-re...
Placing Images with Refined Language Models and Similarity Search with PCA-re...
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013 by Sunando Sengupta
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Sunando Sengupta1.2K views
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ... by mustafa sarac
Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ...
mustafa sarac1.2K views
Enhanced Tracking Aerial Image by Applying Fusion & Image Registration Technique by IRJET Journal
Enhanced Tracking Aerial Image by Applying Fusion & Image Registration TechniqueEnhanced Tracking Aerial Image by Applying Fusion & Image Registration Technique
Enhanced Tracking Aerial Image by Applying Fusion & Image Registration Technique
IRJET Journal27 views

Recently uploaded

Ransomware is Knocking your Door_Final.pdf by
Ransomware is Knocking your Door_Final.pdfRansomware is Knocking your Door_Final.pdf
Ransomware is Knocking your Door_Final.pdfSecurity Bootcamp
59 views46 slides
Five Things You SHOULD Know About Postman by
Five Things You SHOULD Know About PostmanFive Things You SHOULD Know About Postman
Five Things You SHOULD Know About PostmanPostman
36 views43 slides
"Running students' code in isolation. The hard way", Yurii Holiuk by
"Running students' code in isolation. The hard way", Yurii Holiuk "Running students' code in isolation. The hard way", Yurii Holiuk
"Running students' code in isolation. The hard way", Yurii Holiuk Fwdays
17 views34 slides
STPI OctaNE CoE Brochure.pdf by
STPI OctaNE CoE Brochure.pdfSTPI OctaNE CoE Brochure.pdf
STPI OctaNE CoE Brochure.pdfmadhurjyapb
14 views1 slide
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N... by
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...James Anderson
92 views32 slides
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors by
TouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective SensorsTouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensorssugiuralab
21 views15 slides

Recently uploaded(20)

Five Things You SHOULD Know About Postman by Postman
Five Things You SHOULD Know About PostmanFive Things You SHOULD Know About Postman
Five Things You SHOULD Know About Postman
Postman36 views
"Running students' code in isolation. The hard way", Yurii Holiuk by Fwdays
"Running students' code in isolation. The hard way", Yurii Holiuk "Running students' code in isolation. The hard way", Yurii Holiuk
"Running students' code in isolation. The hard way", Yurii Holiuk
Fwdays17 views
STPI OctaNE CoE Brochure.pdf by madhurjyapb
STPI OctaNE CoE Brochure.pdfSTPI OctaNE CoE Brochure.pdf
STPI OctaNE CoE Brochure.pdf
madhurjyapb14 views
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N... by James Anderson
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
James Anderson92 views
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors by sugiuralab
TouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective SensorsTouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors
sugiuralab21 views
Unit 1_Lecture 2_Physical Design of IoT.pdf by StephenTec
Unit 1_Lecture 2_Physical Design of IoT.pdfUnit 1_Lecture 2_Physical Design of IoT.pdf
Unit 1_Lecture 2_Physical Design of IoT.pdf
StephenTec12 views
Data Integrity for Banking and Financial Services by Precisely
Data Integrity for Banking and Financial ServicesData Integrity for Banking and Financial Services
Data Integrity for Banking and Financial Services
Precisely25 views
Powerful Google developer tools for immediate impact! (2023-24) by wesley chun
Powerful Google developer tools for immediate impact! (2023-24)Powerful Google developer tools for immediate impact! (2023-24)
Powerful Google developer tools for immediate impact! (2023-24)
wesley chun10 views
Future of AR - Facebook Presentation by ssuserb54b561
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook Presentation
ssuserb54b56115 views
Piloting & Scaling Successfully With Microsoft Viva by Richard Harbridge
Piloting & Scaling Successfully With Microsoft VivaPiloting & Scaling Successfully With Microsoft Viva
Piloting & Scaling Successfully With Microsoft Viva
Voice Logger - Telephony Integration Solution at Aegis by Nirmal Sharma
Voice Logger - Telephony Integration Solution at AegisVoice Logger - Telephony Integration Solution at Aegis
Voice Logger - Telephony Integration Solution at Aegis
Nirmal Sharma39 views

Scalable Fiducial Tag Localization on a 3D Prior Map via Graph-Theoretic Global Tag-Map Registration [IROS2022]

  • 1. Scalable Fiducial Tag Localization on a 3D Prior Map Via Graph-Theoretic Global Tag-Map Registration Kenji Koide, Shuji Oishi, Masashi Yokozuka, and Atsuhiko Banno National Institute of Advanced Industrial Science and Technology (AIST), Japan
  • 2. Background • Map-based visual localization has been attracting much attention • It is, however, sometimes necessary to rely on visual fiducial tags (aka visual markers) for initialization and fail-safe [Oishi, 2020]
  • 3. Motivation • Deploying many tags on a 3D prior map is sometimes difficult and tedious • Tag positions are often measured by hand; large effort and inaccurate results • We aim to develop an accurate and automatic method to determine tag poses in the environment
  • 4. Proposed Method 1. VIO-based Tag-Relative-Pose Estimation We use an agile camera to observe tags in the environment and estimate the relative poses between tags via landmark SLAM 2. Global Tag-Map Registration We then roughly align tags and a prior map by establishing tag-plane correspondences via graph-theoretic correspondence estimation 3. Estimation Refinement via Direct Camera-Map Alignment Tag and camera poses are refined by directly aligning agile camera images with the prior map and re-optimize all variables under all constraints
  • 5. VIO-based Tag-Relative-Pose Estimation • We use an agile camera and observe each tag in the environment at least once • The tag poses in the VIO frame is estimated via landmark SLAM VIO (VINS-Mono) Tag detections (Apriltags) Pose graph optimization
  • 6. Global Tag-Map Registration • We want to align the estimated tag poses with a prior 3D map without initial guess • The modality difference makes it difficult to apply image matching… Prior 3D map (sparse point cloud) Estimated tag poses (visually detected) Align w/o initial guess
  • 7. Geometry-based Tag-Plane Matching • We assume that most tags are placed on a plane in the environment • We establish tag-plane correspondences to determine the tag-map transformation Detecting planes in the environment 1. Region growing segmentation 2. RANSAC plane detection 3. Fit oriented BBoxes to plane points
  • 8. Geometry-based Tag-Plane Matching • We assume that most tags are placed on a plane in the environment • We establish tag-plane correspondences to determine the tag-map transformation Detecting planes in the environment 1. Region growing segmentation 2. RANSAC plane detection 3. Fit oriented BBoxes to plane points
  • 9. Geometry-based Tag-Plane Matching • We assume that most tags are placed on a plane in the environment • We establish tag-plane correspondences to determine the tag-map transformation Detecting planes in the environment 1. Region growing segmentation 2. RANSAC plane detection 3. Fit oriented BBoxes to plane points
  • 10. Geometry-based Tag-Plane Matching • We assume that most tags are placed on a plane in the environment • We establish tag-plane correspondences to determine the tag-map transformation Detecting planes in the environment 1. Region growing segmentation 2. RANSAC plane detection 3. Fit oriented BBoxes to plane points Plane = (center, normal, lengths)
  • 11. Max-Clique-based Correspondence Estimation • Tag-Plane Correspondence Consistency Graph Vertex: tag-plane correspondence hypothesis Edge: consistency between correspondence hypotheses ℎ𝑖𝑗 does not contradict ℎ𝑘𝑙 (i.e., they are consistent) Tag i corresponds to plane j Tag k corresponds to plane l ℎ𝑖𝑗 ℎ𝑘𝑙
  • 12. Max-Clique-based Correspondence Estimation • Tag-Plane Correspondence Consistency Graph Vertex: tag-plane correspondence hypothesis Edge: consistency between correspondence hypotheses ℎ𝑖𝑗 ℎ𝑘𝑙
  • 13. Max-Clique-based Correspondence Estimation • Tag-Plane Correspondence Consistency Graph Vertex: tag-plane correspondence hypothesis Edge: consistency between correspondence hypotheses • Largest subset of hypotheses that are all mutually consistent (i.e., maximum clique) gives the best explanation for the tag placement in the given map ℎ𝑖𝑗 ℎ𝑘𝑙
  • 14. Tag-Plane Correspondence Consistency • Consistency between tag-plane correspondence hypotheses is determined based on geometric consistency check ℎ𝑖𝑗 ℎ𝑘𝑙 Tag i Tag k Plane j Plane l
  • 15. Tag-Plane Correspondence Consistency • Consistency between tag-plane correspondence hypotheses is determined based on geometric consistency check • We align tag i and plane j and s.t. distance between tag k and plane l Plane j Plane l
  • 16. Tag-Plane Correspondence Consistency • Consistency between tag-plane correspondence hypotheses is determined based on geometric consistency check • We align tag i and plane j and s.t. distance between tag k and plane l • If normal and translation errors between tag k and plane l are smaller than threshold, these hypotheses are mutually consistent Plane j Plane l Normal error Translation error
  • 17. Example Result Planes Tags • While the consistency graph contains many edges, the max-clique can be found very efficiently [Rossi, 2015]
  • 18. Example Result Planes Tags Consistency graph contains 429,735 hypothesis pairs • While the consistency graph contains many edges, the max-clique can be found very efficiently [Rossi, 2015]
  • 19. Example Result Planes Tags Consistency graph contains 429,735 hypothesis pairs Maximum clique consists of 56 tag-plane correspondences found in 92 msec • While the consistency graph contains many edges, the max-clique can be found very efficiently [Rossi, 2015] • Given the tag-plane correspondences, we estimate the tag-map transformation by minimizing normal-to-normal ICP distance [Rusinkiewicz, 2019]
  • 20. Estimation Refinement • We refine the tag poses by directly aligning agile camera images with the map VIO Tag detections Pose graph Direct alignment
  • 21. Estimation Refinement • We refine the tag poses by directly aligning agile camera images with the map • We use the normalized information distance (NID), a mutual information-based cross modal metric, to maximize the co-occurrence of pixel and map intensity values • Tag and camera poses are re-optimized under all the constraints Agile camera image Map rendered with optimized camera pose
  • 22. Evaluation in Simulation • The method is evaluated on the Replica dataset [Savva, 2019] Global tag-map registration : 0.039m / 1.021° Tag localization accuracy : 98% success rate Baseline (FPFH+RANSAC/Teaser) : 26% and 70% Robustness to outlier tags
  • 23. Evaluation in Real Environment • 117 tags were placed in the environment • Tag poses were estimated in 22 minutes (16 min for VIO recording, 6 min for post processing) • Average tag pose error: 0.019m and 2.382° Final estimation result
  • 24. Thank you for your attention!! 24
  • 25. Conclusion • An accurate and scalable method for fiducial tag localization on a 3D prior environmental map is proposed • VIO-based tag relative pose estimation via landmark SLAM • Global tag-map registration based on tag-plane correspondence estimation via maximum clique finding • Estimation refinement via NID-based direct camera-map alignment • The proposed method could localize over 100 tags in 22 minutes • The average tag localization error was about 2 cm