Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

UCrea Repositorio Abierto de la Universidad de Cantabria
Publicación Artículo científico (JournalArticle)

Enhancing stress measurements accuracy control in the construction of long-span bridges

  • Gaute Alonso, Álvaro
  • García Sánchez, David
  • Ramos Gutiérrez, Óscar Ramón|||0000-0002-9800-2375
  • Ntertimanis, Vasileios
This paper introduces new contributions for construction procedures designed to enhance the robustness and precision of stress control in active anchorage and short presetressing units for long span bridges, particularly addressing potential technical risks. The primary focus is on optimizing stress management for bridge stays, suspension cables, and short prestressing units by emphasizing a unifed parameter: stress. The contributions of this research encompass (1) the introduction of advanced load cells for stress control in active anchorages and (2) the implementation of a novel synchronized multi-strain gage load cell network for short prestressing units, crucial in situations where prestressing losses can attain signifcant magnitudes. To validate these advancements, the authors present (3) a practical experience and results obtained from applying these methodologies in monitoring the structural response during the construction of the Tajo Bridge using the cable-stayed cantilever technique., This work has received funding from the Horizon Europe research and innovation program un-der the grant agreement 101103698 (LIAISON project).
UCrea Repositorio Abierto de la Universidad de Cantabria
Publicación Artículo científico (JournalArticle)

Enhancing pavement crack segmentation via semantic diffusion synthesis model for strategic road assessment

  • Cano Ortiz, Saúl|||0000-0003-1383-180X
  • Sainz Ortiz, Eugenio
  • Lloret Iglesias, Lara
  • Martínez Ruiz del Árbol, Pablo|||0000-0002-7737-5121
  • Castro Fresno, Daniel|||0000-0001-5658-3901
Computer-aided deep learning has significantly advanced road crack segmentation. However, supervised models face challenges due to limited annotated images. There is also a lack of emphasis on deriving pavement condition indices from predicted masks. This article introduces a novel semantic diffusion synthesis model that creates synthetic crack images from segmentation masks. The model is optimized in terms of architectural complexity, noise schedules, and condition scaling. The optimal architecture outperforms state-of-the-art semantic synthesis models across multiple benchmark datasets, demonstrating superior image quality assessment metrics. The synthetic frames augment these datasets, resulting in segmentation models with significantly improved efficiency. This approach enhances results without extensive data collection or annotation, addressing a key challenge in engineering. Finally, a refined pavement condition index has been developed for automated end-to-end defect detection systems, promoting more effective maintenance planning., This work has been co-financed by the Ministry of Science and Innovation (ES) through the State Plan for Scientific and Technical Research and Innovation 2021-23 under the project MAPSIA [TED2021-129749B–I00]. Also, by the Horizon Europe Research and Innovation Framework program of the European Union under the project LIAISON [101103698].
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Enhancing pavement crack segmentation via semantic diffusion synthesis model for strategic road assessment

  • Cano Ortiz, Saúl
  • Sainz-Ortiz, Eugenio
  • Lloret Iglesias, Lara
  • Martínez Ruiz del Arbol, P.
  • Castro-Fresno, Daniel
Computer-aided deep learning has significantly advanced road crack segmentation. However, supervised models face challenges due to limited annotated images. There is also a lack of emphasis on deriving pavement condition indices from predicted masks. This article introduces a novel semantic diffusion synthesis model that creates synthetic crack images from segmentation masks. The model is optimized in terms of architectural complexity, noise schedules, and condition scaling. The optimal architecture outperforms state-of-the-art semantic synthesis models across multiple benchmark datasets, demonstrating superior image quality assessment metrics. The synthetic frames augment these datasets, resulting in segmentation models with significantly improved efficiency. This approach enhances results without extensive data collection or annotation, addressing a key challenge in engineering. Finally, a refined pavement condition index has been developed for automated end-to-end defect detection systems, promoting more effective maintenance planning., This work has been co-financed by the Ministry of Science and Innovation (ES) through the State Plan for Scientific and Technical Research and Innovation 2021-23 under the project MAPSIA [TED2021-129749B–I00]. Also, by the Horizon Europe Research and Innovation Framework program of the European Union under the project LIAISON [101103698]., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Leveraging a deep learning generative model to enhance recognition of minor asphalt defects

  • Cano Ortiz, Saúl
  • Sainz-Ortiz, Eugenio
  • Lloret Iglesias, Lara
  • Martínez Ruiz del Arbol, P.
  • Castro-Fresno, Daniel
Deep learning-based computer vision systems have become powerful tools for automated and cost-effective pavement distress detection, essential for efficient road maintenance. Current methods focus primarily on developing supervised learning architectures, which are limited by the scarcity of annotated image datasets. The use of data augmentation with synthetic images created by generative models to improve these supervised systems is not widely explored. The few studies that do focus on generative architectures are mostly non-conditional, requiring extra labeling, and typically address only road crack defects while aiming to improve classification models rather than object detection. This study introduces AsphaltGAN, a novel class-conditional Generative Adversarial Network with attention mechanisms, designed to augment datasets with various rare road defects to enhance object detection. An in-depth analysis evaluates the impact of different loss functions and hyperparameter tuning. The optimized AsphaltGAN outperforms state-of-the-art generative architectures on public datasets. Additionally, a new workflow is proposed to improve object detection models using synthetic road images. The augmented datasets significantly improve the object detection metrics of You Only Look Once version 8 by 33.0 % , 3.8 %, 46.3 %, and 51.8 % on the Road Damage Detection 2022 dataset, Crack Dataset, Asphalt Pavement Detection Dataset, and Crack Surface Dataset, respectively., This work has been co-financed by the Ministry of Science and Innovation (ES) through the State Plan for Scientific and Technical Research and Innovation 2021-23 under the project MAPSIA [TED2021-129749B-I00]. Also, by the Horizon Europe Research and Innovation Framework program of the European Union under the project LIAISON [101103698]., Peer reviewed
UCrea Repositorio Abierto de la Universidad de Cantabria
Publicación Artículo científico (JournalArticle)

Leveraging a deep learning generative model to enhance recognition of minor asphalt defects

  • Cano Ortiz, Saúl|||0000-0003-1383-180X
  • Sainz Ortiz, Eugenio
  • Lloret Iglesias, Lara
  • Martínez Ruiz del Árbol, Pablo|||0000-0002-7737-5121
  • Castro Fresno, Daniel|||0000-0001-5658-3901
Deep learning-based computer vision systems have become powerful tools for automated and cost-effective pavement distress detection, essential for efficient road maintenance. Current methods focus primarily on developing supervised learning architectures, which are limited by the scarcity of annotated image datasets. The use of data augmentation with synthetic images created by generative models to improve these supervised systems is not widely explored. The few studies that do focus on generative architectures are mostly non-conditional, requiring extra labeling, and typically address only road crack defects while aiming to improve classification models rather than object detection. This study introduces AsphaltGAN, a novel class-conditional Generative Adversarial Network with attention mechanisms, designed to augment datasets with various rare road defects to enhance object detection. An in-depth analysis evaluates the impact of different loss functions and hyperparameter tuning. The optimized AsphaltGAN outperforms state-of-the-art generative architectures on public datasets. Additionally, a new workflow is proposed to improve object detection models using synthetic road images. The augmented datasets significantly improve the object detection metrics of You Only Look Once version 8 by 33.0%, 3.8%, 46.3%, and 51.8% on the Road Damage Detection 2022 dataset, Crack Dataset, Asphalt Pavement Detection Dataset, and Crack Surface Dataset, respectively., This work has been co-financed by the Ministry of Science and Innovation (ES) through the State Plan for Scientific and Technical Research and Innovation 2021-23 under the project MAPSIA [TED2021-129749B-I00]. Also, by the Horizon Europe Research and Innovation Framework program of the European Union under the project LIAISON [101103698].