Volumetric Gradient-Aware Methodology for the Exploration of Foreign Objects in the Seabed

• Type: Article in International Conference Proceedings Book
• Date: 2024

Authors

Silva, R (Author) Other; Pereira, P (Author) Other; Aníbal Castilho Coimbra de Matos (Author) FEUP; Pinto, A (Author) FEUP

Conference proceedings International

Title: Oceans Conference Record (IEEE)

Pages: 1-4

OCEANS 2024 - Singapore, OCEANS 2024

Singapore, 15 April 2024 through 18 April 2024

Indexing

Scopus - 0 Citations

Other information

Authenticus ID: P-017-MKN

DOI: 10.1109/oceans55160.2024.10754344

Abstract (EN): The underwater domain presents a myriad of challenges for perception systems that must be overcome to achieve accurate object detection and recognition. To augment the performance and safety of existing solutions for intricate O&M (Operations and Maintenance) procedures, AUVs must perceive the surroundings and locate potential objects of interest based on the perceived information. A depth gradient methodology is employed to survey the seabed using a multibeam sonar to perform a coarse reconstruction of the scenario that it later used to locate and identify foreign objects. This could include rocks, debris, wreckage, or other objects that may pose potential exploratory interest. First results show that the proposed method was able to detect 100 % of the objects present in the scenario with an average chamfer distance error of 0.0238m between models and respective reconstruction. © 2024 IEEE.

Language: English

Type (Professor's evaluation): Scientific