摘要
【目的】针对桥梁、隧道等环境下产生的混凝土裂缝情况复杂、干扰因素多的问题,提出一种改进Unet模型(A-Unet)的裂缝检测方法。【方法】以Unet网络为基础,研究了编码器的深度如何影响模型训练时间、检测精度。在解码过程中设计一种融合空间和通道注意力模块,将高分辨率的浅层特征与上采样获得的深层特征信息赋予不同权重,进一步增强裂缝特征。同时,增加dice损失函数对模型进行评价,减少因检测目标与背景数量相差较大,导致评价不准确的问题。【结果】在测试数据集中进行评价,精确度,MIou,召回率分别达到94.70%,86.16%,91.34%。A-Unet模型检测效果明显优于其他5种模型。【结论】利用该方法检测混凝土裂缝精度得到较大提升,且节约了模型训练时间,提高检测效率。
【Objective】A crack detection method based on improved Unet model(A-Unet)is proposed to solve the problems of complex concrete cracks and many interference factors in bridges,tunnels and other environments.【Method】Firstly,Unet-based network,how the deep of the encoder affects the training time and detection accuracy of the model is studied.Secondly,in the decoder process,a fusion space and channel attention module is designed to give different weights to the high-resolution shallow features and the deep feature information obtained from the upsampling to further enhance the crack features.At the same time,the dice loss function is added to evaluate the model to reduce the problem of inaccurate evaluation caused by the large difference between the number of detected objects and the background.【Result】The proposed method was evaluated in the test data set,the Precision,MIou and Recall rate reached 94.70%,86.16%and 91.34%respectively.Also,the detection effect of A-Unet model is significantly better than the other five models.【Conclusion】The results show that the accuracy of concrete crack detection by this method is greatly improved,and the model training time is saved,and the detection efficiency is improved.
作者
潘远
周双喜
杨丹
Pan Yuan;Zhou Shuangxi;Yang Dan(School of Transportation and Logistics,East China Jiaotong University,Nanchang 330013,China;School of Civil Engineering and Architecture,East China Jiaotong University,Nanchang 330013,China)
出处
《华东交通大学学报》
2024年第1期11-19,共9页
Journal of East China Jiaotong University
基金
国家自然科学基金项目(51968022)
江西省主要学科学术和技术带头人项目(20213BCJL22039)。
关键词
混凝土裂缝
深度学习
注意力机制
裂缝识别
语义分割
concrete crack
deep learning
attention mechanism
crack identification
segmentation
