Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Multimodal Fusion Network for Crack Segmentation with Modified U-Net and Transfer Learning–Based MobileNetV2
https://orcid.org/0000-0002-8158-6837
https://orcid.org/0000-0002-3536-9348
https://orcid.org/0000-0002-2565-9894
This study introduces a state-of-the-art methodology for addressing crack segmentation challenges in structure health monitoring, a crucial concern in infrastructure maintenance. The main objective is to enhance real-time crack monitoring through a cutting-edge multimodal fusion approach that intricately combines a modified U-Net with transfer learning-based MobileNetV2. This integration strategically amalgamates spatial awareness and long-range dependency capture, resulting in an advanced model for crack segmentation. Thorough evaluations of a specialized crack detection data set underscore the efficacy of this integrated approach, positioning it as a reliable solution for real-time crack monitoring. Notably, the choice of MobileNetV2, recognized for its efficiency with the least parameters, contributes to the fusion’s effectiveness. This study reveals superior performance, particularly when MobileNetV2 is integrated with U-Net, demonstrating enhanced accuracy and Intersection over Union (IOU) scores.
Multimodal Fusion Network for Crack Segmentation with Modified U-Net and Transfer Learning–Based MobileNetV2
https://orcid.org/0000-0002-8158-6837
https://orcid.org/0000-0002-3536-9348
https://orcid.org/0000-0002-2565-9894
This study introduces a state-of-the-art methodology for addressing crack segmentation challenges in structure health monitoring, a crucial concern in infrastructure maintenance. The main objective is to enhance real-time crack monitoring through a cutting-edge multimodal fusion approach that intricately combines a modified U-Net with transfer learning-based MobileNetV2. This integration strategically amalgamates spatial awareness and long-range dependency capture, resulting in an advanced model for crack segmentation. Thorough evaluations of a specialized crack detection data set underscore the efficacy of this integrated approach, positioning it as a reliable solution for real-time crack monitoring. Notably, the choice of MobileNetV2, recognized for its efficiency with the least parameters, contributes to the fusion’s effectiveness. This study reveals superior performance, particularly when MobileNetV2 is integrated with U-Net, demonstrating enhanced accuracy and Intersection over Union (IOU) scores.
Multimodal Fusion Network for Crack Segmentation with Modified U-Net and Transfer Learning–Based MobileNetV2
https://orcid.org/0000-0002-8158-6837
https://orcid.org/0000-0002-3536-9348
https://orcid.org/0000-0002-2565-9894
This study introduces a state-of-the-art methodology for addressing crack segmentation challenges in structure health monitoring, a crucial concern in infrastructure maintenance. The main objective is to enhance real-time crack monitoring through a cutting-edge multimodal fusion approach that intricately combines a modified U-Net with transfer learning-based MobileNetV2. This integration strategically amalgamates spatial awareness and long-range dependency capture, resulting in an advanced model for crack segmentation. Thorough evaluations of a specialized crack detection data set underscore the efficacy of this integrated approach, positioning it as a reliable solution for real-time crack monitoring. Notably, the choice of MobileNetV2, recognized for its efficiency with the least parameters, contributes to the fusion’s effectiveness. This study reveals superior performance, particularly when MobileNetV2 is integrated with U-Net, demonstrating enhanced accuracy and Intersection over Union (IOU) scores.
Multimodal Fusion Network for Crack Segmentation with Modified U-Net and Transfer Learning–Based MobileNetV2
J. Infrastruct. Syst.
Qiu, Shi (Autor:in) / Zaheer, Qasim (Autor:in) / Ehsan, Haleema (Autor:in) / Hassan Shah, Syed Muhammad Ahmed (Autor:in) / Ai, Chengbo (Autor:in) / Wang, Jin (Autor:in) / Zheng, Allen A. (Autor:in)
01.12.2024
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Pothole Detection of Road Pavement by Modified MobileNetV2 for Transfer Learning
| Springer Verlag | 2024
| DOAJ | 2025
Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique
| DOAJ | 2023
A Rapid Identification Technique of Moving Loads Based on MobileNetV2 and Transfer Learning
| DOAJ | 2023
RGVPSeg: multimodal information fusion network for retinogeniculate visual pathway segmentation
| Springer Verlag | 2025