摘要
针对现有地铁隧道衬砌渗漏水检测模型检测精度较低、检测速度较慢、抗干扰能力较差的问题,提出轻量化分割模型HMARU-net.采用结合自校准卷积的HC-MobileNetV3作为主干特征提取网络,轻量化模型并提升多尺度特征提取能力.设计部分注意力卷积聚合网络PACANet,通过注意力机制和残差结构,增强全局信息建模和复杂细节特征提取的能力.构建残差模块RAEPC Block组成解码器,减少计算需求,提高分割精度和抗干扰能力.在跳跃连接层引入Attention Gate,有效降低编、解码器之间的语义差异.实验结果表明,HMARU-net的平均交并比、平均像素准确度和准确率分别达到86.0%、93.07%和98.33%.模型复杂度大幅降低,参数量、计算量仅为3.134×10^(6)和6.872×10^(9),图片处理速度达到78.967帧/s.与其他主流语义分割模型相比,HMARU-net显著提升了检测精度与效率,具有较强的轻量化优势.
The lightweight segmentation model HMARU-net was proposed in order to address the issues of low detection accuracy,slow detection speed,and poor interference resistance in existing subway tunnel lining water leakage detection models.HC-MobileNetV3 combined with self-calibrating convolution was employed as the backbone feature extraction network,achieving lightweight modeling while enhancing multi-scale feature extraction capability.The partial attention convolutional aggregation network was designed to enhance global information modeling and complex detail feature extraction through attention mechanism and residual structure.A residual module(RAEPC Block)was incorporated into the decoder to reduce computational demand while improving segmentation accuracy and interference resistance.An Attention Gate introduced in the skip-connection layer effectively mitigated semantic discrepancy between encoder and decoder.The experimental results demonstrated that HMARU-net achieved the mean intersection over union of 86.0%,mean pixel accuracy of 93.07%,and accuracy of 98.33%.Model complexity was significantly reduced,with only 3.134×10^(6)parameters and 6.872×10^(9)computations,enabling image processing speed of 78.967 frames per second.HMARU-net significantly improved detection accuracy and efficiency while offering strong lightweight advantage compared with other mainstream semantic segmentation models.
作者
武晓春
郭宁
WU Xiaochun;GUO Ning(School of Automation and Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)
出处
《浙江大学学报(工学版)》
北大核心
2026年第3期468-477,512,共11页
Journal of Zhejiang University(Engineering Science)
基金
国家自然科学基金资助项目(61661027)
中央引导地方科技发展资金资助项目(24ZYQA044)
甘肃省重点研发计划资助项目(22YF7GA141)。
关键词
渗漏水
语义分割
轻量化
病害检测
深度学习
water leakage
semantic segmentation
lightweight
disease detection
deep learning
