UAS Edge Computing of Energy Infrastructure Damage Assessment

Jordan Bowman; Lexie Yang; Orrin Thomas; Jerry Kirk; Andrew Duncan; David Hughes; Shannon Meade

doi:10.14358/PERS.22-00087R2

UAS Edge Computing of Energy Infrastructure Damage Assessment

Jordan Bowman, Lexie Yang, Orrin Thomas, Jerry Kirk, Andrew Duncan, David Hughes, Shannon Meade

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Energy infrastructure assessments are needed within 72 hours of natural disasters, and previous data collection methods have proven too slow. We demonstrate a scalable end-to-end solution using a prototype unmanned aerial system that performs on-the-edge detection, classification (i.e., damaged or undamaged), and geo-location of utility poles. The prototype is suitable for disaster response because it requires no local communication infrastructure and is capable of autonomous missions. Collections before, during, and after Hurricane Ida in 2021 were used to test the system. The system delivered an F1 score of 0.65 operating with a 2.7 s/frame processing speed with the YOLOv5 large model and an F1 score of 0.55 with a 0.48 s/ frame with the YOLOv5 small model. Geo-location uncertainty in the bottom half of the frame was ~8 m, mostly driven by error in camera pointing measurement. With additional training data to improve performance and detect additional types of features, a fleet of similar drones could autonomously collect actionable post-disaster data.

Original language	English
Pages (from-to)	79-87
Number of pages	9
Journal	Photogrammetric Engineering and Remote Sensing
Volume	89
Issue number	2
DOIs	https://doi.org/10.14358/PERS.22-00087R2
State	Published - 2023

Funding

This material is based upon work supported by the US Department of Energy Office of Cybersecurity, Energy Security, and Emergency Response. The authors would also like to acknowledge the technical editing and document preparation assistance provided by Laurie Varma (ORNL). Notice: This manuscript has been authored by UT-Battelle LLC under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/ doe-public-access-plan).

Funders	Funder number
DOE Public Access Plan
Laurie Varma
U.S. Department of Energy
Oak Ridge National Laboratory
UT-Battelle	DE-AC05-00OR22725

Access to Document

10.14358/PERS.22-00087R2

Cite this

@article{36062a079a9b41cd95554a60a35a85db,

title = "UAS Edge Computing of Energy Infrastructure Damage Assessment",

abstract = "Energy infrastructure assessments are needed within 72 hours of natural disasters, and previous data collection methods have proven too slow. We demonstrate a scalable end-to-end solution using a prototype unmanned aerial system that performs on-the-edge detection, classification (i.e., damaged or undamaged), and geo-location of utility poles. The prototype is suitable for disaster response because it requires no local communication infrastructure and is capable of autonomous missions. Collections before, during, and after Hurricane Ida in 2021 were used to test the system. The system delivered an F1 score of 0.65 operating with a 2.7 s/frame processing speed with the YOLOv5 large model and an F1 score of 0.55 with a 0.48 s/ frame with the YOLOv5 small model. Geo-location uncertainty in the bottom half of the frame was ~8 m, mostly driven by error in camera pointing measurement. With additional training data to improve performance and detect additional types of features, a fleet of similar drones could autonomously collect actionable post-disaster data.",

author = "Jordan Bowman and Lexie Yang and Orrin Thomas and Jerry Kirk and Andrew Duncan and David Hughes and Shannon Meade",

note = "Publisher Copyright: {\textcopyright} 2023 American Society for Photogrammetry and Remote Sensing.",

year = "2023",

doi = "10.14358/PERS.22-00087R2",

language = "English",

volume = "89",

pages = "79--87",

journal = "Photogrammetric Engineering and Remote Sensing",

issn = "0099-1112",

number = "2",

}

TY - JOUR

T1 - UAS Edge Computing of Energy Infrastructure Damage Assessment

AU - Bowman, Jordan

AU - Yang, Lexie

AU - Thomas, Orrin

AU - Kirk, Jerry

AU - Duncan, Andrew

AU - Hughes, David

AU - Meade, Shannon

PY - 2023

Y1 - 2023

N2 - Energy infrastructure assessments are needed within 72 hours of natural disasters, and previous data collection methods have proven too slow. We demonstrate a scalable end-to-end solution using a prototype unmanned aerial system that performs on-the-edge detection, classification (i.e., damaged or undamaged), and geo-location of utility poles. The prototype is suitable for disaster response because it requires no local communication infrastructure and is capable of autonomous missions. Collections before, during, and after Hurricane Ida in 2021 were used to test the system. The system delivered an F1 score of 0.65 operating with a 2.7 s/frame processing speed with the YOLOv5 large model and an F1 score of 0.55 with a 0.48 s/ frame with the YOLOv5 small model. Geo-location uncertainty in the bottom half of the frame was ~8 m, mostly driven by error in camera pointing measurement. With additional training data to improve performance and detect additional types of features, a fleet of similar drones could autonomously collect actionable post-disaster data.

AB - Energy infrastructure assessments are needed within 72 hours of natural disasters, and previous data collection methods have proven too slow. We demonstrate a scalable end-to-end solution using a prototype unmanned aerial system that performs on-the-edge detection, classification (i.e., damaged or undamaged), and geo-location of utility poles. The prototype is suitable for disaster response because it requires no local communication infrastructure and is capable of autonomous missions. Collections before, during, and after Hurricane Ida in 2021 were used to test the system. The system delivered an F1 score of 0.65 operating with a 2.7 s/frame processing speed with the YOLOv5 large model and an F1 score of 0.55 with a 0.48 s/ frame with the YOLOv5 small model. Geo-location uncertainty in the bottom half of the frame was ~8 m, mostly driven by error in camera pointing measurement. With additional training data to improve performance and detect additional types of features, a fleet of similar drones could autonomously collect actionable post-disaster data.

UR - http://www.scopus.com/inward/record.url?scp=85151796015&partnerID=8YFLogxK

U2 - 10.14358/PERS.22-00087R2

DO - 10.14358/PERS.22-00087R2

M3 - Article

AN - SCOPUS:85151796015

SN - 0099-1112

VL - 89

SP - 79

EP - 87

JO - Photogrammetric Engineering and Remote Sensing

JF - Photogrammetric Engineering and Remote Sensing

IS - 2

ER -

UAS Edge Computing of Energy Infrastructure Damage Assessment

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this