Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation
 
conference paper

On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation

Mouzakidou, Kyriaki  
•
Stoltz, Thibaut  
•
Jospin, Laurent V.  
Show more
Sefercik, Umut Gunes
May 19, 2025
EARSeL and DGPF Joint Istanbul Workshop on Topographic Mapping from Space

The evolution of airborne mapping witnesses the introduction of hybrid lidar-camera systems to enhance data collection, i.e. to obtain simultaneously high-density point-cloud and texture. Yet, the common adjustment of both optical data streams is a nontrivial problem due to challenges associated with the different influences of errors affecting their mapping accuracy including those coming from navigation sensors. Stemming from a special form of graph-based optimization, the dynamic networks allow rigorous modeling of spatio-temporal constraints and thus provide the common framework for optimizing original observations from inertial systems with those coming from optical sensors. In this work, we propose a cross-domain observation model that leverages pixel-to-point correspondences as links between imagery and lidar returns. First, we describe how the existence of such correspondences can be introduced into optimizations. Second, we employ a reference dataset to emulate a set of precise pixel-to-point correspondences to assess its prospective impact on the common (rather than cascade) optimization. We report the improvement in the estimated trajectory attitude error with lower quality IMU and thus the point-cloud registration. Finally, we study whether such correspondences could be contained from freely available deep learning networks with the desired accuracy and quality. We conclude that although the introduction of such camera-to-lidar constraints has significant potential, none of the studied machine learning networks can fulfill the requirement on correspondence detection in terms of quality.

  • Files
  • Details
  • Metrics
Type
conference paper
DOI
10.5194/isprs-archives-XLVIII-M-6-2025-213-2025
Scopus ID

2-s2.0-105009049794

Author(s)
Mouzakidou, Kyriaki  

École Polytechnique Fédérale de Lausanne

Stoltz, Thibaut  

École Polytechnique Fédérale de Lausanne

Jospin, Laurent V.  

École Polytechnique Fédérale de Lausanne

Cucci, Davide A.  

École Polytechnique Fédérale de Lausanne

Skaloud, Jan  

École Polytechnique Fédérale de Lausanne

Editors
Sefercik, Umut Gunes
Date Issued

2025-05-19

Publisher

International Society for Photogrammetry and Remote Sensing

Book part title

ISPRS, EARSeL & DGPF Joint Istanbul Workshop “Topographic Mapping from Space” dedicated to Dr. Karsten Jacobsen’s 80th Birthday

Book part number

XLVIII-M-6-2025

Series title/Series vol.

International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives; 48

ISSN (of the series)

1682-1750

Issue

M-6-2025

Start page

213

End page

220

Subjects

Dynamic networks

•

Learned cross-domain matching

•

Pixel-to-point correspondences

•

Trajectory correction

•

topomapp

•

ESOLAB

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
ESO  
Event nameEvent acronymEvent placeEvent date
EARSeL and DGPF Joint Istanbul Workshop on Topographic Mapping from Space

Istanbul, Türkiye

2025-01-29 - 2025-01-31

FunderFunding(s)Grant NumberGrant URL

Swiss Innovation Agency

119.293,53622.1

Available on Infoscience
July 5, 2025
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/251940
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés