Classification Model Based on U-Net for Crack Detection from Asphalt Pavement Images
Classification Model Based on U-Net for Crack Detection from Asphalt Pavement Images
复制标题
DOI：
10.18178/joig.11.2.121-126
复制
发表时间：
2023-06
影响因子：
--
通讯作者：
Y. Fujita;Taisei Tanaka;Tomoki Hori;Y. Hamamoto
中科院分区：
文献类型：
--
作者：
Y. Fujita;Taisei Tanaka;Tomoki Hori;Y. Hamamoto
我们的研究的目的是准确地检测裂缝从沥青路面的表面图像，其中包括意外的对象，不均匀的照明，和表面的不规则性。我们提出了一种基于预训练的U-Net构建分类卷积神经网络（CNN）模型的方法，这是一种众所周知的语义分割模型。首先，我们用有限数量的沥青路面数据集，这是由一个移动的地图系统（MMS）获得的U-网络训练。然后，我们使用训练好的U-Net的编码器作为特征提取器来构建分类模型，并通过微调进行训练。我们描述了与VGG 11，ResNet 18和GoogLeNet的比较评估，这些模型是通过使用ImageNet的迁移学习构建的，ImageNet是一个大规模的自然图像数据集。实验结果表明，与使用ImageNet通过迁移学习构建的其他模型相比，我们的模型具有较高的分类性能。该方法可以有效地利用有限的训练数据集构造卷积神经网络模型。
The purpose of our study is to detect cracks accurately from asphalt pavement surface images, which includes unexpected objects, non-uniform illumination, and irregularities in surfaces. We propose a method to construct a classification Convolutional Neural Network (CNN) model based on the pre-trained U-Net, which is a well-known semantic segmentation model. Firstly, we train the U-Net with a limited amount of the asphalt pavement surface dataset which is obtained by a Mobile Mapping System (MMS). Then, we use the encoder of the trained U-Net as a feature extractor to construct a classification model, and train by fine-tuning. We describe comparative evaluations with VGG11, ResNet18, and GoogLeNet as well-known models constructed by transfer learning using ImageNet, which is a large size dataset of natural images. Experimental results show our model has high classification performance, compared to the other models constructed by transfer learning using ImageNet. Our method is effective to construct convolutional neural network model using the limited training dataset.