摘要
路面裂缝对行车安全有很大的潜在威胁,以往的人工检测方法效率不高。现有裂缝检测方法模型泛化能力低,在复杂背景下的裂缝分割能力差且效率不高。为了解决这些问题,文中提出了一种基于编码器-解码器结构的新改进型网络结构CrackU-Net,目的是提高路面裂缝检测的模型泛化性以及检测精度。首先,Crack U-Net用密集连接结构增强了基于编码器-解码器的网络U-Net模型,在以往结构的基础上提高了网络各层特征信息利用率,增强了模型的鲁棒性;其次,Crack U-Net使用由残差块和mini-U组成的CrackU-block作为网络的基础卷积模块,相比传统双层卷积层,Crack U-block可以提取出更丰富的裂缝特征;最后,在Crack U-Net的下采样节点中使用了空洞卷积替代传统卷积核,以充分捕获图像边缘的裂缝特征。为验证Crack U-Net模型的有效性,在公开裂缝数据集上进行了一系列测试。实验结果显示,CrackU-Net在数据集上的AIU值比以往方法提升了2.2%,在裂缝分割精度、泛化性上都优于现有方法。另外,参数轻量化部分的实验证明,CrackU-Net可以进行很大程度的模型剪枝,无人机等移动设备将可满足剪枝后的Crack U-Net模型所需的计算资源。
Pavement cracks constitute a major potential threat to driving safety.Previous manual detection methods are highly subjective and inefficient.Current computer vision methods have limited applications in crack detection.Existing models have poor generalization capabilities and limited detection effects.To address this problem,a dense network structure of pavement crack detection,called Crack U-Net,is proposed to improve the model generalization capabilities and detection accuracy.Firstly,the dense connection structure of Crack U-Net adopts the network design from the encoder-decoder backbone network U-Net.Similar to the encoder-decoder backbone network,this structure of Crack U-Net is able to improve the utilization of feature information and to enhance the robustness of the model,as well.Secondly,the Crack U-block composed of residual blocks and mini-U is proposed as the basic convolution module of the network,which can extract more abundant crack features compared with the traditional double-layer convolution layer.Finally,dilated convolution is used in the middle layer of up sampling and down sampling in the network to fully capture the crack features,which is at the edge if the image.Crack U-Net runs on public fracture dataset and produces a series of experimental results.The experimental results show that the AIUvalue of this method on the dataset is 2.2%higher than the previous method,and it is better than the existing fracture segmentation accuracy and generalization.The experimental results also show that Crack U-Net model can be pruned,and the pruned model is suitable for loading to mobile devices for road crack detection.
作者
祝一帆
王海涛
李可
吴贺俊
ZHU Yi-fan;WANG Hai-tao;LI Ke;WU He-jun(School of Computer Science and Engineering,SunYet-San University,Guangzhou 510006,China)
出处
《计算机科学》
CSCD
北大核心
2022年第1期204-211,共8页
Computer Science
基金
国家自然科学基金(61672552)
广州市科技计划项目(202002020045)。
关键词
道路路面
裂缝检测
深度学习
图像分割
Road pavement
Crack detection
Deep learning
Image segmentation
