• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于卷积神经网络的无人机驱动结构裂缝检测与定位

UAV-Driven Structural Crack Detection and Location Determination Using Convolutional Neural Networks.

机构信息

Department of Aerospace Engineering & Engineering Mechanics, University of Cincinnati, Cincinnati, OH 45221, USA.

Dynetics, Huntsville, AL 35806, USA.

出版信息

Sensors (Basel). 2021 Apr 9;21(8):2650. doi: 10.3390/s21082650.

DOI:10.3390/s21082650
PMID:33918951
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8069420/
Abstract

Structural cracks are a vital feature in evaluating the health of aging structures. Inspectors regularly monitor structures' health using visual information because early detection of cracks on highly trafficked structures is critical for maintaining the public's safety. In this work, a framework for detecting cracks along with their locations is proposed. Image data provided by an unmanned aerial vehicle (UAV) is stitched using image processing techniques to overcome limitations in the resolution of cameras. This stitched image is analyzed to identify cracks using a deep learning model that makes judgements regarding the presence of cracks in the image. Moreover, cracks' locations are determined using data from UAV sensors. To validate the system, cracks forming on an actual building are captured by a UAV, and these images are analyzed to detect and locate cracks. The proposed framework is proven as an effective way to detect cracks and to represent the cracks' locations.

摘要

结构裂缝是评估老化结构健康状况的重要特征。检查人员通常使用视觉信息定期监测结构的健康状况，因为及早发现高流量结构上的裂缝对于维护公众安全至关重要。在这项工作中，提出了一种用于检测裂缝及其位置的框架。使用图像处理技术拼接由无人机 (UAV) 提供的图像数据，以克服相机分辨率的限制。使用深度学习模型分析拼接后的图像，以判断图像中是否存在裂缝。此外，使用无人机传感器的数据确定裂缝的位置。为了验证该系统，使用无人机捕捉实际建筑物上形成的裂缝，然后对这些图像进行分析以检测和定位裂缝。该框架被证明是一种有效的检测裂缝并表示裂缝位置的方法。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/4a2c40a59a92/sensors-21-02650-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/4fb7ca567e5a/sensors-21-02650-g0A1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/1dd639a51710/sensors-21-02650-g0A2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/702488315a12/sensors-21-02650-g0A3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/e8652f553e1d/sensors-21-02650-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/a60a7cc7febd/sensors-21-02650-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/e2974f6334b1/sensors-21-02650-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/ad6e1e4f3095/sensors-21-02650-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/326180b7f1bb/sensors-21-02650-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/c862e3f50a50/sensors-21-02650-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/948e814e557c/sensors-21-02650-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/0b2afe4865f4/sensors-21-02650-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/6e7e609d4a96/sensors-21-02650-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/5386205d7fb2/sensors-21-02650-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/6153a91fc32f/sensors-21-02650-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/1c6a4634978d/sensors-21-02650-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/4a2c40a59a92/sensors-21-02650-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/4fb7ca567e5a/sensors-21-02650-g0A1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/1dd639a51710/sensors-21-02650-g0A2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/702488315a12/sensors-21-02650-g0A3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/e8652f553e1d/sensors-21-02650-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/a60a7cc7febd/sensors-21-02650-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/e2974f6334b1/sensors-21-02650-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/ad6e1e4f3095/sensors-21-02650-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/326180b7f1bb/sensors-21-02650-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/c862e3f50a50/sensors-21-02650-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/948e814e557c/sensors-21-02650-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/0b2afe4865f4/sensors-21-02650-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/6e7e609d4a96/sensors-21-02650-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/5386205d7fb2/sensors-21-02650-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/6153a91fc32f/sensors-21-02650-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/1c6a4634978d/sensors-21-02650-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec6/8069420/4a2c40a59a92/sensors-21-02650-g013.jpg

相似文献

1
UAV-Driven Structural Crack Detection and Location Determination Using Convolutional Neural Networks.基于卷积神经网络的无人机驱动结构裂缝检测与定位
Sensors (Basel). 2021 Apr 9;21(8):2650. doi: 10.3390/s21082650.
2
Application of Crack Identification Techniques for an Aging Concrete Bridge Inspection Using an Unmanned Aerial Vehicle.应用裂缝识别技术对使用无人机进行的老化混凝土桥梁检测
Sensors (Basel). 2018 Jun 8;18(6):1881. doi: 10.3390/s18061881.
3
Concrete Crack Identification Using a UAV Incorporating Hybrid Image Processing.使用结合混合图像处理的无人机进行混凝土裂缝识别
Sensors (Basel). 2017 Sep 7;17(9):2052. doi: 10.3390/s17092052.
4
Using Deep Learning and Low-Cost RGB and Thermal Cameras to Detect Pedestrians in Aerial Images Captured by Multirotor UAV.利用深度学习以及低成本的 RGB 和热成像摄像机，检测多旋翼无人机航拍图像中的行人。
Sensors (Basel). 2018 Jul 12;18(7):2244. doi: 10.3390/s18072244.
5
A Novel Approach for UAV Image Crack Detection.一种用于无人机图像裂缝检测的新方法。
Sensors (Basel). 2022 Apr 26;22(9):3305. doi: 10.3390/s22093305.
6
Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges.将 YOLOv4 深度学习模型与无人机图像处理技术相结合，用于桥梁裂缝的提取和量化。
Sensors (Basel). 2023 Feb 25;23(5):2572. doi: 10.3390/s23052572.
7
Automatic Pixel-Level Crack Detection on Dam Surface Using Deep Convolutional Network.基于深度卷积网络的大坝表面像素级裂缝自动检测
Sensors (Basel). 2020 Apr 7;20(7):2069. doi: 10.3390/s20072069.
8
Crack Length Measurement Using Convolutional Neural Networks and Image Processing.使用卷积神经网络和图像处理进行裂纹长度测量。
Sensors (Basel). 2021 Sep 1;21(17):5894. doi: 10.3390/s21175894.
9
Vision-Based Autonomous Crack Detection of Concrete Structures Using a Fully Convolutional Encoder-Decoder Network.基于视觉的混凝土结构自主裂缝检测：使用全卷积编解码网络。
Sensors (Basel). 2019 Sep 30;19(19):4251. doi: 10.3390/s19194251.
10
Vision and Deep Learning-Based Algorithms to Detect and Quantify Cracks on Concrete Surfaces from UAV Videos.基于视觉和深度学习的算法，用于从无人机视频中检测和量化混凝土表面的裂缝。
Sensors (Basel). 2020 Nov 5;20(21):6299. doi: 10.3390/s20216299.

引用本文的文献

1
Machine-Aided Bridge Deck Crack Condition State Assessment Using Artificial Intelligence.基于人工智能的桥面裂缝状态评估
Sensors (Basel). 2023 Apr 22;23(9):4192. doi: 10.3390/s23094192.
2
Euclidean Graphs as Crack Pattern Descriptors for Automated Crack Analysis in Digital Images.欧几里得图作为数字图像中自动裂纹分析的裂纹模式描述符。
Sensors (Basel). 2022 Aug 9;22(16):5942. doi: 10.3390/s22165942.
3
Fatigue Crack Evaluation with the Guided Wave-Convolutional Neural Network Ensemble and Differential Wavelet Spectrogram.

本文引用的文献

1
Computer Vision-Based Bridge Damage Detection Using Deep Convolutional Networks with Expectation Maximum Attention Module.基于深度卷积网络和期望最大化注意力模块的计算机视觉桥梁损伤检测。
Sensors (Basel). 2021 Jan 26;21(3):824. doi: 10.3390/s21030824.
2
Flame Image Processing and Classification Using a Pre-Trained VGG16 Model in Combustion Diagnosis.使用预训练的 VGG16 模型进行燃烧诊断中的火焰图像处理和分类。
Sensors (Basel). 2021 Jan 12;21(2):500. doi: 10.3390/s21020500.
3
Vision and Deep Learning-Based Algorithms to Detect and Quantify Cracks on Concrete Surfaces from UAV Videos.
基于导波-卷积神经网络集成和差分小波谱的疲劳裂纹评估。
Sensors (Basel). 2021 Dec 31;22(1):307. doi: 10.3390/s22010307.
基于视觉和深度学习的算法，用于从无人机视频中检测和量化混凝土表面的裂缝。
Sensors (Basel). 2020 Nov 5;20(21):6299. doi: 10.3390/s20216299.
4
CNN Training with Twenty Samples for Crack Detection via Data Augmentation.通过数据增强用二十个样本进行 CNN 裂缝检测训练。
Sensors (Basel). 2020 Aug 27;20(17):4849. doi: 10.3390/s20174849.
5
Disease Classification in Eggplant Using Pre-trained VGG16 and MSVM.利用预训练的 VGG16 和 MSVM 对茄子进行疾病分类。
Sci Rep. 2020 Feb 11;10(1):2322. doi: 10.1038/s41598-020-59108-x.
6
Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning.基于深度学习的自动图像植物病害严重程度估计
Comput Intell Neurosci. 2017;2017:2917536. doi: 10.1155/2017/2917536. Epub 2017 Jul 5.
7
Using Deep Learning for Image-Based Plant Disease Detection.利用深度学习进行基于图像的植物病害检测。
Front Plant Sci. 2016 Sep 22;7:1419. doi: 10.3389/fpls.2016.01419. eCollection 2016.