{"title":"From manual to UAV-based inspection: Efficient detection of levee seepage hazards driven by thermal infrared image and deep learning","authors":"Baili Chen , Quntao Duan , Lihui Luo","doi":"10.1016/j.ijdrr.2024.104982","DOIUrl":null,"url":null,"abstract":"<div><div>Levee failures are caused mainly by river water seepage erosion inside the levee, manifesting as slope leakage and foundation piping phenomena. To address the urgent need for levee safety monitoring during flood seasons and extreme rainfall events, unmanned aerial vehicles (UAVs) equipped with thermal infrared imagers can quickly detect leakage and piping hazards based on temperature differences between damaged areas and their surroundings. In this study, we collected 5995 UAV thermal infrared images of leakage and piping on levees in four floodplains under various weather, time, and surface coverage conditions to evaluate the applicability of combining thermal infrared imaging with a deep learning model in complex natural environments. We categorized levee hazards into water piping, ground piping, and slope leakage, and developed a Mask R-CNN segmentation model. The results revealed that thermal infrared levee inspection was affected by vegetation occlusion and subtle temperature differences caused by continuous rainstorms and water body depth. The Mask R-CNN demonstrated strong generalizability to hazards with significant variability in shape, size, and temperature difference, making it suitable for detecting evolving and expanding damaged area. The mean average precision, recall, and precision of the Mask R-CNN were 0.977, 0.982, and 0.897, respectively, and the detection time was 0.015 s per image. Moreover, Eigenvector-based class activation mapping (Eigen-CAM) was used to visualize the decision basis and failure modes of the Mask R-CNN to improve interpretability. Seepage damage is a progressive process, so timely hazard identification can provide valuable time for levee repair.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104982"},"PeriodicalIF":4.2000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International journal of disaster risk reduction","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212420924007441","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Levee failures are caused mainly by river water seepage erosion inside the levee, manifesting as slope leakage and foundation piping phenomena. To address the urgent need for levee safety monitoring during flood seasons and extreme rainfall events, unmanned aerial vehicles (UAVs) equipped with thermal infrared imagers can quickly detect leakage and piping hazards based on temperature differences between damaged areas and their surroundings. In this study, we collected 5995 UAV thermal infrared images of leakage and piping on levees in four floodplains under various weather, time, and surface coverage conditions to evaluate the applicability of combining thermal infrared imaging with a deep learning model in complex natural environments. We categorized levee hazards into water piping, ground piping, and slope leakage, and developed a Mask R-CNN segmentation model. The results revealed that thermal infrared levee inspection was affected by vegetation occlusion and subtle temperature differences caused by continuous rainstorms and water body depth. The Mask R-CNN demonstrated strong generalizability to hazards with significant variability in shape, size, and temperature difference, making it suitable for detecting evolving and expanding damaged area. The mean average precision, recall, and precision of the Mask R-CNN were 0.977, 0.982, and 0.897, respectively, and the detection time was 0.015 s per image. Moreover, Eigenvector-based class activation mapping (Eigen-CAM) was used to visualize the decision basis and failure modes of the Mask R-CNN to improve interpretability. Seepage damage is a progressive process, so timely hazard identification can provide valuable time for levee repair.
期刊介绍:
The International Journal of Disaster Risk Reduction (IJDRR) is the journal for researchers, policymakers and practitioners across diverse disciplines: earth sciences and their implications; environmental sciences; engineering; urban studies; geography; and the social sciences. IJDRR publishes fundamental and applied research, critical reviews, policy papers and case studies with a particular focus on multi-disciplinary research that aims to reduce the impact of natural, technological, social and intentional disasters. IJDRR stimulates exchange of ideas and knowledge transfer on disaster research, mitigation, adaptation, prevention and risk reduction at all geographical scales: local, national and international.
Key topics:-
-multifaceted disaster and cascading disasters
-the development of disaster risk reduction strategies and techniques
-discussion and development of effective warning and educational systems for risk management at all levels
-disasters associated with climate change
-vulnerability analysis and vulnerability trends
-emerging risks
-resilience against disasters.
The journal particularly encourages papers that approach risk from a multi-disciplinary perspective.