2018
DOI: 10.1111/mice.12375
|View full text |Cite
|
Sign up to set email alerts
|

Autonomous UAVs for Structural Health Monitoring Using Deep Learning and an Ultrasonic Beacon System with Geo‐Tagging

Abstract: Visual inspection has traditionally been used for structural health monitoring. However, assessments conducted by trained inspectors or using contact sensors on structures for monitoring are costly and inefficient because of the number of inspectors and sensors required. To date, data acquisition using unmanned aerial vehicles (UAVs) equipped with cameras has become popular, but UAVs require skilled pilots or a global positioning system (GPS) for autonomous flight. Unfortunately, GPS cannot be used by a UAV fo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4

Citation Types

0
161
0
5

Year Published

2019
2019
2024
2024

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 295 publications
(166 citation statements)
references
References 38 publications
0
161
0
5
Order By: Relevance
“…Particularly for aerial imagery, however, additional issues may arise and will need to be solved. Kang and Cha [7] highlight several challenges that need to be addressed before applying our approach outside of a manufacturing setting.…”
Section: Introductionmentioning
confidence: 99%
“…Particularly for aerial imagery, however, additional issues may arise and will need to be solved. Kang and Cha [7] highlight several challenges that need to be addressed before applying our approach outside of a manufacturing setting.…”
Section: Introductionmentioning
confidence: 99%
“…The rapid development of Machine Learning (ML) and Deep Learning (DL) technologies and great improvement of Graphics Processing Unit (GPU) hardware motivate further developments and applications toward Artificial Intelligence (AI) and Intelligence Augmentation (IA) research area in many fields of science and engineering. Even in the traditional Civil and Structural Engineering areas, increased number of studies related to ML and DL have been taking place and resulting in promising findings (Kang & Cha, ; Lin, Nie, & Ma, ; Maeda, Sekimoto, Seto, Kashiyama, & Omata, ; Nabian & Meidani, ; Oh, Kim, Kim, Park, and Adeli, ; Rafiei & Adeli, , ; Rafiei, Khushefati, Demirboga, & Adeli, ; Yeum, Dyke, Ramirez, & Benes, ). Many of these studies applied DL in computer vision‐based Structural Health Monitoring (SHM).…”
Section: Introductionmentioning
confidence: 99%
“…The rapid development of Machine Learning (ML) and Deep Learning (DL) technologies and great improvement of Graphics Processing Unit (GPU) hardware motivate further developments and applications toward Artificial Intelligence (AI) and Intelligence Augmentation (IA) research area in many fields of science and engineering. Even in the traditional Civil and Structural Engineering areas, increased number of studies related to ML and DL have been taking place and resulting in promising findings (Kang & Cha, 2018;Lin, Nie, & Ma, 2017;Maeda, Sekimoto, Seto, Kashiyama, & Omata, 2018;Nabian & Meidani, 2018;Oh, Kim, Kim, Park, and series of experiments on detecting structural component type and damage severity and type on structural object level based on a small data set, where Transfer Learning (TL) and online Affine Data Augmentation (ADA) were applied. These two methods, that is, TL and ADA, effectively alleviated the negative influence (namely, overfitting) of labeled data deficiency.…”
Section: Introductionmentioning
confidence: 99%
“…Therefore, a more carefully configured deep neural network (DNN) is essential for solving the true variety of real‐world problems. For example, different DNNs have been proposed to identify cracks in images with disturbing background interference (F. C. Chen & Jahanshahi, ; Kang & Cha, ; R. Li, Yuan, Zhang, & Yuan, ; Liang, ; Y. Xu, Bao et al., ). In addition, the noising issues and the layer multiplexing scheme in DNNs have been discussed (Koziarski & Cyganek, ; Ortega‐Zamorano, Jerez, Gómez, & Franco, ).…”
Section: Introductionmentioning
confidence: 99%