Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Automatic crack detection on concrete and asphalt surfaces using semantic segmentation network with hierarchical Transformer
Abstract In recent studies, deep learning methodologies have shown significant promise in crack detection. However, their practical implementation faces challenges due to the intricate diversity of structural surfaces and the inherent narrowness of cracks. To mitigate these problems, this paper introduces SegFormer, an efficient semantic segmentation model with hierarchical Transformer, for crack detection on concrete and asphalt surfaces in multiple scenarios. The combination of Cross-Entropy (CE) and Dice loss functions is employed to enhance the detection of fine cracks. Additionally, the paper presents an evaluation framework and discusses metrics for assessing crack segmentation results to provide a more precise and comprehensive analysis of model performance. Experimental results indicate that SegFormer outperforms Convolutional Neural Networks (CNNs) such as FCN, U-Net, and DeepLabV3 utilizing different backbones. Notably, the integration of multiple loss functions contributes to a more stable training process, expedites convergence, and yields enhanced results compared to models utilizing individual loss functions.
Highlights SegFormer is introduced for fine crack detection in various scenarios. The combination of CE and Dice loss functions enhances crack detection. A comprehensive model evaluation framework is presented. Metrics for fine crack segmentation assessment are discussed.
Automatic crack detection on concrete and asphalt surfaces using semantic segmentation network with hierarchical Transformer
Abstract In recent studies, deep learning methodologies have shown significant promise in crack detection. However, their practical implementation faces challenges due to the intricate diversity of structural surfaces and the inherent narrowness of cracks. To mitigate these problems, this paper introduces SegFormer, an efficient semantic segmentation model with hierarchical Transformer, for crack detection on concrete and asphalt surfaces in multiple scenarios. The combination of Cross-Entropy (CE) and Dice loss functions is employed to enhance the detection of fine cracks. Additionally, the paper presents an evaluation framework and discusses metrics for assessing crack segmentation results to provide a more precise and comprehensive analysis of model performance. Experimental results indicate that SegFormer outperforms Convolutional Neural Networks (CNNs) such as FCN, U-Net, and DeepLabV3 utilizing different backbones. Notably, the integration of multiple loss functions contributes to a more stable training process, expedites convergence, and yields enhanced results compared to models utilizing individual loss functions.
Highlights SegFormer is introduced for fine crack detection in various scenarios. The combination of CE and Dice loss functions enhances crack detection. A comprehensive model evaluation framework is presented. Metrics for fine crack segmentation assessment are discussed.
Automatic crack detection on concrete and asphalt surfaces using semantic segmentation network with hierarchical Transformer
Li, Hubing (Autor:in) / Zhang, Haowei (Autor:in) / Zhu, Hong (Autor:in) / Gao, Kang (Autor:in) / Liang, Hanbin (Autor:in) / Yang, Jiangjin (Autor:in)
Engineering Structures ; 307
21.03.2024
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
| Wiley | 2022