Highway image crack detection based on U-Net architecture and UAV aerial sensor

CHEN Wei; CHEN Ken; ZHU Wenyao

Chinese

您当前的位置：

首页 >

文章列表页 >

Highway image crack detection based on U-Net architecture and UAV aerial sensor

Calculation & Test | 更新时间：2026-03-01

- Highway image crack detection based on U-Net architecture and UAV aerial sensor
- Vol. 45, Issue 2, Pages: 161-166(2026)
- 作者机构：
  
  1. 浙江交投高速公路营运管理有限公司,浙江,丽水,323000
  2. 浙江容祺科技有限公司,浙江,丽水,323000
  3. 丽水学院数学与计算机学院,浙江,丽水,323000
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP212;TP391
- Published：2026
- 稿件说明：
移动端阅览
CHEN Wei, CHEN Ken, ZHU Wenyao. Highway image crack detection based on U-Net architecture and UAV aerial sensor[J]. 2026, 45(2): 161-166.
DOI：

CHEN Wei, CHEN Ken, ZHU Wenyao. Highway image crack detection based on U-Net architecture and UAV aerial sensor[J]. 2026, 45(2): 161-166. DOI：

摘要

针对当前模型对公路裂缝检测不精确的问题，提出了一种基于无人机(UAV)航拍传感器遥感图像的智能检测方法。基于U-Net架构，结合深度可分离残差块（DR-Block）、空间金字塔融合注意力模块（SPFAM）和感受野块（RFB），提出DARUnet逐像素裂缝检测模型。利用无人机采集1046张高质量公路遥感图像构建专用数据集。在自制数据集上，DAR-Unet的平均交并比（mIoU）和F1分数分别达到76.41%和74.24%，高于主流模型。进一步将模型与无人机集成，构建了公路裂缝检测物联网系统，实际测试表现优异，验证了DAR-Unet在遥感图像公路裂缝检测中的有效性。

Abstract

To address the inaccurate detection of highway cracks by current models

an intelligent detection method based on remote sensing images from unmanned aerial vehicle(UAV)aerial sensors is proposed.Based on the U-Net architecture

the DAR-Unet pixel-wise crack detection model is developed by combining the deeply separable residual block(DR-Block)

the spatial pyramid fusion attention module(SPFAM)

and the receptive field block(RFB).A dedicated dataset is constructed using 1046 high-quality highway remote sensing images collected by UAVs.On this self-developed dataset

DAR-Unet achieves a mean intersection over union(mIoU)and an F1-score of 76.41% and 74.24%

respectively

which are higher than those of mainstream models.The model is further integrated with UAVs to construct an Internet of Things-based highway crack detection system.Practical tests show excellent performance

verifying the effectiveness of DAR-Unet in highway crack detection using remote sensing images.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Resilience multi-sensor UAV localization based on a hybrid joint fusion architecture

Spatiotemporal fusion of cross-scale remote sensing images based on multi-source sensors

Multi-objective 3D UAV motion planning in WSN based on particle swarm optimization

Research on multi-UAV cooperative localization method of grassland fire point

3D UAV track planning based on improved A^* algorithm in complex terrain

Related Author

YANG Congmin

HU Haizhou

ZHANG Wenjuan

ZHU Lei

ZHENG Ying

JI Song

AN Juanhua

LU Xiuli

Related Institution

College of Information and Management Science,Henan Agricultural University

School of Electrical and Information Engineering,Zhengzhou University

School of Mechanical and Electrical Engineering,Henan Vocational University of Science and Technology

Information Technology College,Guangxi Police College

School of Information Science and Engineering,Baoding University of Technology

⁰