Mid Sweden University

miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Enabling Autonomous Structural Inspections with Tiny Machine Learning on UAVs
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0002-8617-0435
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0002-2336-5390
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0001-9572-3639
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0002-8382-0359
2024 (English)In: 2024 IEEE Sensors Applications Symposium, SAS 2024 - Proceedings, IEEE conference proceedings, 2024Conference paper, Published paper (Refereed)
Abstract [en]

Visual structural inspections in Structural Health Monitoring (SHM) are an important method to ensure the safety and long lifetime of infrastructures. Unmanned Aerial Vehicles (UAVs) with Deep Learning (DL) have gained in popularity to automate these inspections. Yet, the vast majority of research focuses on algorithmic innovations that neglect the availability of reliable generalized DL models, as well as the effect that the model's energy consumption would have on the UAV flight time. This paper highlights the performance of 14 popular CNN models with less than six million parameters for crack detection in concrete structures. Seven of these models were successfully deployed to a low-power, resource-constrained mi-crocontroller using Tiny Machine Learning (TinyML). Among the deployed models, MobileNetV1-x0.25 achieves the highest test accuracy (75.83%) and F1-Score (0.76), the second-lowest flash memory usage (273.5 kB), the second-lowest RAM usage (317.1kB), the fourth-fastest single-trial inference time (15.8ms), and the fourth-lowest number of Multiply-Accumulate operations (MACC) (42126514). Lastly, a hypothetical study of the DJI Mini 4 Pro UAV demonstrated that the TinyML model's energy consumption has a negligible impact on the UAV flight time (34 minutes vs. 33.98 minutes). Consequently, this feasibility study paves the way for future developments towards more efficient, autonomous unmanned structural health inspections. 

Place, publisher, year, edition, pages
IEEE conference proceedings, 2024.
Keywords [en]
convolutional neural networks, damage classification, embedded systems, structure health monitoring, Tiny machine learning, unmanned aerial vehicles
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:miun:diva-52591DOI: 10.1109/SAS60918.2024.10636583ISI: 001304520300085Scopus ID: 2-s2.0-85203704393ISBN: 9798350369250 (print)OAI: oai:DiVA.org:miun-52591DiVA, id: diva2:1900649
Conference
2024 IEEE Sensors Applications Symposium, SAS 2024 - Proceedings
Available from: 2024-09-24 Created: 2024-09-24 Last updated: 2024-11-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Zhang, YuxuanMartinez Rau, LucianoOelmann, BengtBader, Sebastian

Search in DiVA

By author/editor
Zhang, YuxuanMartinez Rau, LucianoOelmann, BengtBader, Sebastian
By organisation
Department of Computer and Electrical Engineering (2023-)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 62 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf