Pérez-García De La Puente, NL.; Del Amor, R.; García-Torres, F.; Colomer, A.; Naranjo Ornedo, V. (2023). Unsupervised Defect Detection for Infrastructure Inspection. Springer. 142-153. https://doi.org/10.1007/978-3-031-48232-8_14
Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10251/203857
Título:
|
Unsupervised Defect Detection for Infrastructure Inspection
|
Autor:
|
Pérez-García de la Puente, Natalia Lourdes
del Amor, Rocío
García-Torres, Fernando
Colomer, Adrián
Naranjo Ornedo, Valeriana
|
Entidad UPV:
|
Universitat Politècnica de València. Escuela Técnica Superior de Ingenieros de Telecomunicación - Escola Tècnica Superior d'Enginyers de Telecomunicació
Universitat Politècnica de València. Escuela Técnica Superior de Ingeniería del Diseño - Escola Tècnica Superior d'Enginyeria del Disseny
|
Fecha difusión:
|
|
Resumen:
|
[EN] Artificial Intelligence (AI) provides a fundamental aid in building operations, allowing infrastructure inspection and compliance with safety standards. In the collaborative tasks involved, detecting areas of interest, ...[+]
[EN] Artificial Intelligence (AI) provides a fundamental aid in building operations, allowing infrastructure inspection and compliance with safety standards. In the collaborative tasks involved, detecting areas of interest, such as surface defects, is crucial. A drawback of supervised AI-based approaches is that they require manual annotation, which entails additional costs. This paper presents a novel unsupervised anomaly detection approach for locating defects based on generative models that learn the distribution of defect-free images. Using attention maps to validate in a subset, we propose a formulation that does not require accessing labelled images, enabling task automation, maintenance optimisation and cost reduction.
[-]
|
Palabras clave:
|
Visual Inspection
,
Infrastructure Inspection
,
Defects
,
Unsupervised Segmentation
|
Derechos de uso:
|
Reserva de todos los derechos
|
ISBN:
|
978-3-031-48232-8
|
Fuente:
|
Intelligent Data Engineering and Automated Learning - IDEAL 2023. IDEAL 2023. Lecture Notes in Computer Science, vol 14404.
|
DOI:
|
10.1007/978-3-031-48232-8_14
|
Editorial:
|
Springer
|
Versión del editor:
|
https://doi.org/10.1007/978-3-031-48232-8_14
|
Título del congreso:
|
24th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2023)
|
Lugar del congreso:
|
Évora, Portugal
|
Fecha congreso:
|
Noviembre 22-24,2023
|
Código del Proyecto:
|
info:eu-repo/grantAgreement/EC/HE/101057404/EU/Non-Destructive Inspection Services for Digitally Enhanced Zero Waste Manufacturing/
info:eu-repo/grantAgreement/EC/HE/101058054/EU/Towards tURbine Blade production with zero waste/
info:eu-repo/grantAgreement/MIU//FPU20%2F05263/
|
Agradecimientos:
|
This work has received funding from Horizon Europe, the European Union¿s
Framework Programme for Research and Innovation, under Grant Agreement No.
101058054 (TURBO) and No. 101057404 (ZDZW). The work of Rocio del Amor ...[+]
This work has received funding from Horizon Europe, the European Union¿s
Framework Programme for Research and Innovation, under Grant Agreement No.
101058054 (TURBO) and No. 101057404 (ZDZW). The work of Rocio del Amor has
been supported by the Spanish Ministry of Universities (FPU20/05263).
[-]
|
Tipo:
|
Comunicación en congreso
Capítulo de libro
|