Enhancing Underwater Inspection Capabilities: A Learning-Based Approach for Automated Pipeline Visibility Assessment

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2024

Autores

Mina, J (Autor) Outra; Leite, PN (Autor) Outra; Carvalho, J (Autor) Outra; Pinho, L (Autor) Outra; Gonçalves, EP (Autor) Outra; Pinto, AM (Autor) FEUP

Ata de Conferência Internacional

Título: ROBOT 2023: SIXTH IBERIAN ROBOTICS CONFERENCE, VOL 2

Páginas: 162-173

6th Iberian Robotics Conference (Robot)

Coimbra, PORTUGAL, NOV 22-24, 2023

Indexação

ISI Web of Knowledge - 0 Citações

Scopus - 0 Citações

Outras Informações

ID Authenticus: P-010-EW5

DOI: 10.1007/978-3-031-59167-9_14

Abstract (EN): Underwater scenarios pose additional challenges to perception systems, as the collected imagery from sensors often suffers from limitations that hinder its practical usability. One crucial domain that relies on accurate underwater visibility assessment is underwater pipeline inspection. Manual assessment is impractical and time-consuming, emphasizing the need for automated algorithms. In this study, we focus on developing learning-based approaches to evaluate visibility in underwater environments. We explore various neural network architectures and evaluate them on data collected within real subsea scenarios. Notably, the ResNet18 model outperforms others, achieving a testing accuracy of 93.5% in visibility evaluation. In terms of inference time, the fastest model is MobileNetV3 Small, estimating a prediction within 42.45 ms. These findings represent significant progress in enabling unmanned marine operations and contribute to the advancement of autonomous underwater surveillance systems.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 12