Result: Vision-based 3D Reconstruction for Deep-Sea Environments: Practical Use for Surveys and Inspection

Title:
Vision-based 3D Reconstruction for Deep-Sea Environments: Practical Use for Surveys and Inspection
Authors:
Ferrera, Maxime, Arnaubec, Aurélien, Boittiaux, Clémentin, Larroche, Inès, Opderbecke, Jan
Contributors:
Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER), Laboratoire Conception de Systèmes Mécaniques et Robotiques - EA 7398 (COSMER), Université de Toulon (UTLN), Laboratoire d'Informatique et des Systèmes (LIS) (Marseille, Toulon) (LIS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)
Source:
OCEANS 2023 - Limerick. :1-7
Publisher Information:
CCSD; IEEE, 2023.
Publication Year:
2023
Collection:
collection:UNIV-TLN
collection:CNRS
collection:UNIV-AMU
collection:IFREMER
collection:COSMER
collection:LIS-LAB
collection:INCIAM
Subject Terms:
[INFO.INFO-CV]Computer Science [cs], Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-RB]Computer Science [cs], Robotics [cs.RO]
Subject Geographic:
Limerick, Ireland
Original Identifier:
HAL: hal-04206629
Document Type:
Conference conferenceObject<br />Conference papers
Language:
English
Relation:
info:eu-repo/semantics/altIdentifier/doi/10.1109/OCEANSLimerick52467.2023.10244338
DOI:
10.1109/OCEANSLimerick52467.2023.10244338
Access URL:
https://hal.science/hal-04206629
https://hal.science/hal-04206629v1/document
https://hal.science/hal-04206629v1/file/Oceans%202023%20-%20Ferrera.pdf
Rights:
info:eu-repo/semantics/OpenAccess
Accession Number:
edshal.hal.04206629v1
Database:
HAL

Further Information

This paper presents a combination of real-time and offline 3D reconstruction methods for remotely operated vehicles (ROVs) equipped with cameras used in underwater inspection and survey tasks. The real-time component is based on a stereo visual simultaneous localization and mapping algorithm and a truncated signed distance field representation for producing a coarse online 3D reconstruction. The offline component uses structure-from-motion techniques to create a dense point cloud representation of the scene which is then meshed and textured to produce a high-quality textured 3D mesh. The paper highlights the feasibility of using ROVs for vision-based 3D reconstruction in real-world scenarios and the potential of combining real-time and offline processing in practice for a range of underwater applications.