摘要
为解决现有混凝土桥梁数字图像方法缺陷识别单一、分割精度较低等问题,本文提出了一种基于编解码架构的精细化语义分割模型HDNet。编码器设计方面,采用层级化窗口自注意力机制,通过滑动窗口划分结合跨层残差连接增强梯度传播。引入核化注意力模块强化侵蚀、裂缝等局部缺陷的梯度响应,抑制桥梁背景纹理干扰。解码器设计像素-变形双路径架构体现在像素路径通过逐点特征映射解析裂缝等形态细节,变形路径采用可变形卷积自适应匹配剥落区域的不规则几何轮廓。基于无人机采集的高清桥梁缺陷数据集(涵盖裂缝、侵蚀、露筋、剥落4类缺陷),开展与DeepLabV3+、SegFormer等主流模型的对比实验,随后进行消融实验分析、热力图分析和实桥测试。结果表明:HDNet验证集交并比(mIoU)达71.91%,较次优模型SegFormer提升了7.86%;消融性实验验证了核化注意力(提升召回率mRecall 5.83%)、层次化滑窗注意力(提升mIoU 5.92%)与Dice损失函数协同设计的必要性;热力图分析证实HDNet能够精准捕捉缺陷纹理细节并解耦伴生缺陷的语义边界;实桥测试中,HDNet将缺陷尺寸测量相对误差稳定控制在±5%以内,验证了其在实际应用中的适用性。HDNet通过编解码协同优化与跨分辨率层次化增强机制,有效提升复杂桥梁缺陷的识别精度与鲁棒性,可为桥梁表观病害智能化检测提供高精度技术手段。
To address the issues of single-category defect identification and low segmentation accuracy in current digital image-based methods for concrete bridge defect detection,a refined semantic segmentation model named HDNet,which is built upon an encoder-decoder architecture,was introduced.In terms of encoder design,a hierarchical window-based self-attention mechanism was implemented,which combinnes sliding window partitioning and cross-layer residual connections to enhance gradient propagation.A kernelized attention module was incorporated to strengthen gradient responses for local defects,such as erosion and cracks,while simultaneously reducing interference from the background texture of the bridge.A pixel-deformation dual-path architecture was adopted in the decoder,in which the pixel path employs pointwise feature mapping to capture the morphological details of cracks and the deformation path utilizes deformable convolutions to adaptively match the irregular geometric contours of spalling regions.A series of experiments were carried out on a high-resolution dataset of bridge defects including four categories of defects:cracks,erosion,exposed rebar,and spalling,which was captured by unmanned aerial vehicle(UAV).Comparisons with those dominant models such as DeepLabV3+and SegFormer were performed,and then ablation study analysis,heatmap analysis and real-bridge validation were carried out.The results indicate that HDNet attains a mean Intersection over Union(mIoU)of 71.91%on the validation set,surpassing the suboptimal model SegFormer by 7.86%.Ablation studies validate the necessity of kernelized attention(which improves mRecall by 5.83%),hierarchical sliding-window attention(which boosts mIoU by 5.92%),and the synergistic design with the Dice loss function.Heatmap analysis demonstrates HDNet’s ability to accurately capture defect texture details and disentangle the semantic boundaries of co-occurring defects.In real-bridge testing,HDNet maintains the relative error of defect size measurement within±5%,which confirms its practical applicability.By integrating encoder-decoder co-optimization and cross-resolution hierarchical enhancement mechanisms,HDNet substantially enhances the recognition accuracy and robustness for complex bridge defects,thereby offering a high-precision technology for the intelligent detection of bridge surface deterioration.
作者
周勇军
罗楠
孙延晨
尚嘉琪
陈炽毅
ZHOU Yongjun;LUO Nan;SUN Yanchen;SHANG Jiaqi;CHEN Chiyi(School of Highway,Chang an University,Xi'an 710064,China;Shanghai Municipal Traffic Design and Research Institute Co.,Ltd.,Shanghai 200030,China)
出处
《哈尔滨工业大学学报》
北大核心
2025年第6期103-115,共13页
Journal of Harbin Institute of Technology
基金
国家重点研发计划(2021YFB2601000)
国家自然科学基金(52278138)
中央高校基本科研业务费资助项目(300102214301)。
关键词
桥梁工程
混凝土表观缺陷
语义分割
深度学习
注意力机制
无人机
bridge engineering
concrete surface defects
semantic segmentation
deep learning
attention mechanism
unmanned aerial vehicle(UAV)
作者简介
周勇军(1978-),男,教授,博士生导师;通信作者:周勇军,zyj@chd.edu.cn。
