测绘科学技术学报2025，Vol.41Issue(1)：49-56,8.DOI:10.3969/j.issn.1673-6338.2025.01.008
一种基于ASPPUnet的道路裂缝检测模型
A Pavement Crack Detection Model Based on ASPPUnet
摘要
Abstract
In order to segment and extract pavement cracks more accurately and efficiently,an ASPPUnet pavement crack detection model is proposed based on multi-scale features and context information fusion in this paper.In AS-PPUnet,multi-scale features are extracted through U-shaped Encoder-Decoder,and context information of different ranges is fused by introducing ASPP module.And depthwise separable convolution is introduced into the model to realize lightweight of the model.The loss function of fusion Dice and cross entropy is adopted to balance the recall and precision of the model.Meanwhile,dynamic dataset augmentation method is adopted to achieve good detection effect on small data sets.Compared with Unet and other models,ASPPUnet has better detection effect and plastici-ty,which leads to better application value.关键词
裂缝检测/图像分割/深度可分离卷积/损失函数/ASPP模块/Unet模型Key words
crack detection/image segmentation/depthwise separable convolution/loss function/ASPP(Atrous Spatial Pynamid Pooling)/Unet分类
测绘与仪器引用本文复制引用
曹一冰,张江水,张政,赵鑫科..一种基于ASPPUnet的道路裂缝检测模型[J].测绘科学技术学报,2025,41(1):49-56,8.基金项目
国家重点研发计划项目(2021YFB3900900). （2021YFB3900900）
