| dc.contributor.author | López Fuster, Miguel Ángel | |
| dc.contributor.author | Morgado Estévez, Arturo | |
| dc.contributor.author | Díaz Cano, Ignacio | |
| dc.contributor.author | Badesa Clemente, Francisco Javier | |
| dc.contributor.other | Ingeniería en Automática, Electrónica, Arquitectura y Redes de Computadores | es_ES |
| dc.contributor.other | Ingeniería Informática | es_ES |
| dc.date.accessioned | 2025-03-06T11:19:21Z | |
| dc.date.available | 2025-03-06T11:19:21Z | |
| dc.date.issued | 2024 | |
| dc.identifier.issn | 2075-1702 | |
| dc.identifier.uri | http://hdl.handle.net/10498/35749 | |
| dc.description.abstract | This paper presents a novel approach for extracting 3D weld point information using a
two-stage deep learning pipeline based on readily available 2D RGB cameras. Our method utilizes
YOLOv8s for object detection, specifically targeting vertices, followed by semantic segmentation for
precise pixel localization. This pipeline addresses the challenges posed by low-contrast images and
complex geometries, significantly reducing costs compared with traditional 3D-based solutions. We
demonstrated the effectiveness of our approach through a comparison with a 3D-point-cloud-based
method, showcasing the potential for improved speed and efficiency. This research advances the
field of automated welding by providing a cost-effective and versatile solution for extracting key
information from 2D images. | es_ES |
| dc.format | application/pdf | es_ES |
| dc.language.iso | eng | es_ES |
| dc.publisher | MDPI | es_ES |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
| dc.source | Machines - 2024, Vol. 12 n. 7 pp. 1-20 | es_ES |
| dc.subject | initial weld point | es_ES |
| dc.subject | robotic welding | es_ES |
| dc.subject | object detection | es_ES |
| dc.subject | robotics | es_ES |
| dc.subject | computer vision | es_ES |
| dc.subject | point cloud | es_ES |
| dc.subject | shipbuilding | es_ES |
| dc.subject | intelligent welding | es_ES |
| dc.subject | YOLO | es_ES |
| dc.title | A Neural-Network-Based Cost-Effective Method for Initial Weld Point Extraction from 2D Images | es_ES |
| dc.type | journal article | es_ES |
| dc.rights.accessRights | open access | es_ES |
| dc.identifier.doi | 10.3390/MACHINES12070447 | |
| dc.relation.projectID | EQC2018-005190-P | es_ES |
| dc.type.hasVersion | VoR | es_ES |