UAV-Based Structural Health Monitoring Using a Two-Stage CNN Model with Lighthouse Localization in GNSS-Denied Environments

This study presents a UAV-based Structural Health Monitoring (SHM) system that combines Lighthouse localization with a two-stage CNN architecture—AlexNet for crack classification and YOLOv4 for segmentation—to enable reliable crack detection and spatial mapping in GNSS-denied environments. This stu...

Full description

Saved in:
Bibliographic Details
Main Authors: Timothy Scott C. Chu, Joses Sorilla, Alvin Y. Chua
Format: Article
Language:English
Published: Ital Publication 2025-06-01
Series:HighTech and Innovation Journal
Subjects:
Online Access:https://hightechjournal.org/index.php/HIJ/article/view/1100
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849249071264432128
author Timothy Scott C. Chu
Joses Sorilla
Alvin Y. Chua
author_facet Timothy Scott C. Chu
Joses Sorilla
Alvin Y. Chua
author_sort Timothy Scott C. Chu
collection DOAJ
description This study presents a UAV-based Structural Health Monitoring (SHM) system that combines Lighthouse localization with a two-stage CNN architecture—AlexNet for crack classification and YOLOv4 for segmentation—to enable reliable crack detection and spatial mapping in GNSS-denied environments. This study explores the effectiveness of this combination as a practical and computationally efficient solution for indoor SHM tasks. The UAV was deployed within a 1.5 m × 1.2 m × 1.2 m test volume to inspect synthetic cracks derived from Özgenel’s dataset, as well as a real-world wall crack. Two experiments were conducted: evaluating UAV localization accuracy and assessing the system’s ability to detect cracks and provide corresponding pose data. The system achieved a 1–2 cm margin of error in pose estimation, alongside 100% precision, 83.33% recall, and 91.89% accuracy in crack detection. This level of localization accuracy supports stable autonomous UAV flight and ensures that cracks are detected and spatially localized with minimal deviation. Beyond classification and segmentation, the system returns pose data tied to each detected crack, allowing users to identify defect locations precisely and use this information to guide inspection or maintenance tasks. Future work includes expanding the dataset, generalization, and evaluating scalability via multi-base station setups.
format Article
id doaj-art-48e8d7fc68f0432aafb57914ed7015b5
institution Kabale University
issn 2723-9535
language English
publishDate 2025-06-01
publisher Ital Publication
record_format Article
series HighTech and Innovation Journal
spelling doaj-art-48e8d7fc68f0432aafb57914ed7015b52025-08-20T03:57:40ZengItal PublicationHighTech and Innovation Journal2723-95352025-06-016210.28991/HIJ-2025-06-02-03UAV-Based Structural Health Monitoring Using a Two-Stage CNN Model with Lighthouse Localization in GNSS-Denied EnvironmentsTimothy Scott C. Chu0https://orcid.org/0000-0001-5775-1532Joses Sorilla1Alvin Y. Chua2https://orcid.org/0000-0003-0954-7291Department of Mechanical Engineering, De La Salle University, 2401 Taft Ave. Malate, ManilaDepartment of Mechanical Engineering, De La Salle University, 2401 Taft Ave. Malate, ManilaDepartment of Mechanical Engineering, De La Salle University, 2401 Taft Ave. Malate, Manila This study presents a UAV-based Structural Health Monitoring (SHM) system that combines Lighthouse localization with a two-stage CNN architecture—AlexNet for crack classification and YOLOv4 for segmentation—to enable reliable crack detection and spatial mapping in GNSS-denied environments. This study explores the effectiveness of this combination as a practical and computationally efficient solution for indoor SHM tasks. The UAV was deployed within a 1.5 m × 1.2 m × 1.2 m test volume to inspect synthetic cracks derived from Özgenel’s dataset, as well as a real-world wall crack. Two experiments were conducted: evaluating UAV localization accuracy and assessing the system’s ability to detect cracks and provide corresponding pose data. The system achieved a 1–2 cm margin of error in pose estimation, alongside 100% precision, 83.33% recall, and 91.89% accuracy in crack detection. This level of localization accuracy supports stable autonomous UAV flight and ensures that cracks are detected and spatially localized with minimal deviation. Beyond classification and segmentation, the system returns pose data tied to each detected crack, allowing users to identify defect locations precisely and use this information to guide inspection or maintenance tasks. Future work includes expanding the dataset, generalization, and evaluating scalability via multi-base station setups. https://hightechjournal.org/index.php/HIJ/article/view/1100Crack DetectionCrack SegmentationGNSS-Denied EnvironmentsLighthouse LocalizationStructural Health MonitoringTwo-Stage CNN Model
spellingShingle Timothy Scott C. Chu
Joses Sorilla
Alvin Y. Chua
UAV-Based Structural Health Monitoring Using a Two-Stage CNN Model with Lighthouse Localization in GNSS-Denied Environments
HighTech and Innovation Journal
Crack Detection
Crack Segmentation
GNSS-Denied Environments
Lighthouse Localization
Structural Health Monitoring
Two-Stage CNN Model
title UAV-Based Structural Health Monitoring Using a Two-Stage CNN Model with Lighthouse Localization in GNSS-Denied Environments
title_full UAV-Based Structural Health Monitoring Using a Two-Stage CNN Model with Lighthouse Localization in GNSS-Denied Environments
title_fullStr UAV-Based Structural Health Monitoring Using a Two-Stage CNN Model with Lighthouse Localization in GNSS-Denied Environments
title_full_unstemmed UAV-Based Structural Health Monitoring Using a Two-Stage CNN Model with Lighthouse Localization in GNSS-Denied Environments
title_short UAV-Based Structural Health Monitoring Using a Two-Stage CNN Model with Lighthouse Localization in GNSS-Denied Environments
title_sort uav based structural health monitoring using a two stage cnn model with lighthouse localization in gnss denied environments
topic Crack Detection
Crack Segmentation
GNSS-Denied Environments
Lighthouse Localization
Structural Health Monitoring
Two-Stage CNN Model
url https://hightechjournal.org/index.php/HIJ/article/view/1100
work_keys_str_mv AT timothyscottcchu uavbasedstructuralhealthmonitoringusingatwostagecnnmodelwithlighthouselocalizationingnssdeniedenvironments
AT josessorilla uavbasedstructuralhealthmonitoringusingatwostagecnnmodelwithlighthouselocalizationingnssdeniedenvironments
AT alvinychua uavbasedstructuralhealthmonitoringusingatwostagecnnmodelwithlighthouselocalizationingnssdeniedenvironments