Deep Learning-Based 3D Reconstruction for Defect Detection in Shipbuilding Sub-Assemblies

Overshooting defects in shipbuilding subassemblies are essential to ensure the final product’s overall integrity and safety. In this work, we focus on the automatic detection of overshooting defects in simple and T-shaped sub-assemblies by employing reconstruction-based unsupervised learning on 3D p...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Paula Arcano-Bea, Agustín García-Fischer, Pedro-Pablo Gómez-González, Francisco Zayas-Gato, José Luis Calvo-Rolle, Héctor Quintián
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2026-01-01
Schriftenreihe:	Sensors
Schlagworte:	3D point clouds overshooting defects unsupervised anomaly detection reconstruction-based autoencoders Isolation Forest shipbuilding
Online-Zugang:	https://www.mdpi.com/1424-8220/26/2/660
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!