Autonomous health assessment of civil infrastructure using deep learning and smart devices

Damage detection via drones is fundamental in infrastructure health assessment. However, object scale variation due to drones' swift movement and sparse scenes make damage detection challenging. This paper describes a multi-task framework, EnsembleDetNet, for damage detection and multi-label sc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Automation in construction 2022-09, Vol.141, p.104396, Article 104396
Hauptverfasser: Agyemang, Isaac Osei, Zhang, Xiaoling, Acheampong, Daniel, Adjei-Mensah, Isaac, Kusi, Goodlet Akwasi, Mawuli, Bernard Cobbinah, Agbley, Bless Lord Y.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Damage detection via drones is fundamental in infrastructure health assessment. However, object scale variation due to drones' swift movement and sparse scenes make damage detection challenging. This paper describes a multi-task framework, EnsembleDetNet, for damage detection and multi-label scene classification by leveraging object detectors and classifiers based on ensemble learning which induces diversity and strength-correlation. Further, a novel attention module that significantly improves EnsembleDetNet by about 5% is proposed via explicit ensembling of parallel and sequential channel and spatial attention maps. Extensive experiments with a public dataset and an onsite verification utilizing a micro drone indicate that EsembleDetNet outperforms state-of-the-art detectors and classifiers under variant evaluation metrics. EnsembleDetNet has the potential to become a new paradigm in infrastructure health assessment. •EnsembleDetNet, a generic multi-task framework, is proposed.•A novel explicit attention module that significantly boosts performance is proposed.•Engineering practicability is demonstrated for structural health assessment.•EnsembleDetNet attains better performance in detection and multi-label scene tasks.
ISSN:0926-5805
1872-7891
DOI:10.1016/j.autcon.2022.104396