当前位置:
X-MOL 学术
›
Autom. Constr.
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Automatic crack defect detection via multiscale feature aggregation and adaptive fusion
Automation in Construction ( IF 9.6 ) Pub Date : 2024-12-21 , DOI: 10.1016/j.autcon.2024.105934
Hanyun Huang, Mingyang Ma, Suli Bai, Lei Yang, Yanhong Liu
Automation in Construction ( IF 9.6 ) Pub Date : 2024-12-21 , DOI: 10.1016/j.autcon.2024.105934
Hanyun Huang, Mingyang Ma, Suli Bai, Lei Yang, Yanhong Liu
In this paper, a multi-scale feature aggregation and adaptive fusion network, is proposed for automatic and accurate pavement crack defect segmentation. Specifically, faced with the linear characteristic of pavement crack defects, a multiple-dimension attention (MDA) module is proposed to effectively capture long-range correlation from three directions, including space, width and height, and help identify the pavement crack defect boundaries. On this basis, a multi-scale skip connection (MSK) module is proposed, which can effectively utilize the feature information from multiple receptive fields to support accurate feature reconstruction in the decoding stage. Furthermore, a multi-scale attention fusion (MSAF) module is proposed to realize effective multi-scale feature representation and aggregation. Finally, an adaptive weight fusion (AWL) module is proposed to dynamically fuse the output features across different network layers for accurate multi-scale crack defect segmentation. Experiments indicate that proposed network is superior to other mainstream segmentation networks on pixelwise crack defect detection task.
中文翻译:
通过多尺度特征聚合和自适应融合自动检测裂纹缺陷
该文提出了一种多尺度特征聚合和自适应融合网络,用于自动、准确地分割路面裂缝缺陷。具体来说,面对路面裂缝缺陷的线性特征,提出了一种多维注意力 (MDA) 模块,以有效捕获空间、宽度和高度三个方向的长期相关性,并帮助识别路面裂缝缺陷边界。在此基础上,该文提出一种多尺度跳跃连接(MSK)模块,该模块可以有效利用来自多个感受野的特征信息,以支持解码阶段的准确特征重建。此外,该文提出一种多尺度注意力融合(MSAF)模块,以实现有效的多尺度特征表示和聚合。最后,提出了一种自适应权重融合 (AWL) 模块,用于动态融合不同网络层的输出特征,以实现精确的多尺度裂纹缺陷分割。实验表明,所提出的网络在像素级裂纹缺陷检测任务上优于其他主流分割网络。
更新日期:2024-12-21
中文翻译:

通过多尺度特征聚合和自适应融合自动检测裂纹缺陷
该文提出了一种多尺度特征聚合和自适应融合网络,用于自动、准确地分割路面裂缝缺陷。具体来说,面对路面裂缝缺陷的线性特征,提出了一种多维注意力 (MDA) 模块,以有效捕获空间、宽度和高度三个方向的长期相关性,并帮助识别路面裂缝缺陷边界。在此基础上,该文提出一种多尺度跳跃连接(MSK)模块,该模块可以有效利用来自多个感受野的特征信息,以支持解码阶段的准确特征重建。此外,该文提出一种多尺度注意力融合(MSAF)模块,以实现有效的多尺度特征表示和聚合。最后,提出了一种自适应权重融合 (AWL) 模块,用于动态融合不同网络层的输出特征,以实现精确的多尺度裂纹缺陷分割。实验表明,所提出的网络在像素级裂纹缺陷检测任务上优于其他主流分割网络。