Preliminary analysis of reconstructions from aerial images of disaster props

Traci A. Sarmiento, Brittany A Duncan, Robin R. Murphy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper provides a preliminary analysis of reconstructions of seven disaster props from datasets collected over five flights with a small unmanned aerial vehicle and finds 181 anomalies present in four categories. Commercial and free software are available to create reconstructions from digital images, but their accuracy and limitations have not been formally explored for disaster assessment. This work analyzes the output of two packages, Agisoft Photoscan, and Microsoft ICE for five image datasets of seven Disaster City®props. The 181 anomalous results are divided into four categories: ghosting, misalignment, misproportions, and the Dali effect. These metrics are valuable to Urban Search and Rescue teams, structural specialists, and insurance claims adjusters who need to reliably assess whether it is safe to enter a building, or accurately estimate the severity of damage. The analysis suggests the reconstructions might be misleading and further work must be done to determine why and suggest methods of improvement.

Original languageEnglish (US)
Title of host publicationSSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509019595
DOIs
StatePublished - Mar 29 2016
EventIEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2015 - West Lafayette, United States
Duration: Oct 18 2015Oct 20 2015

Publication series

NameSSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics

Other

OtherIEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2015
CountryUnited States
CityWest Lafayette
Period10/18/1510/20/15

Fingerprint

Disasters
disaster
reconstruction
Antennas
insurance claim
Insurance
Unmanned aerial vehicles (UAV)
flight
damages
present
software

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering
  • Safety Research

Cite this

Sarmiento, T. A., Duncan, B. A., & Murphy, R. R. (2016). Preliminary analysis of reconstructions from aerial images of disaster props. In SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics [7443004] (SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSRR.2015.7443004

Preliminary analysis of reconstructions from aerial images of disaster props. / Sarmiento, Traci A.; Duncan, Brittany A; Murphy, Robin R.

SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics. Institute of Electrical and Electronics Engineers Inc., 2016. 7443004 (SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sarmiento, TA, Duncan, BA & Murphy, RR 2016, Preliminary analysis of reconstructions from aerial images of disaster props. in SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics., 7443004, SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics, Institute of Electrical and Electronics Engineers Inc., IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2015, West Lafayette, United States, 10/18/15. https://doi.org/10.1109/SSRR.2015.7443004
Sarmiento TA, Duncan BA, Murphy RR. Preliminary analysis of reconstructions from aerial images of disaster props. In SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics. Institute of Electrical and Electronics Engineers Inc. 2016. 7443004. (SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics). https://doi.org/10.1109/SSRR.2015.7443004
Sarmiento, Traci A. ; Duncan, Brittany A ; Murphy, Robin R. / Preliminary analysis of reconstructions from aerial images of disaster props. SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics. Institute of Electrical and Electronics Engineers Inc., 2016. (SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics).
@inproceedings{88814db2b6d040149191521432c17d52,
title = "Preliminary analysis of reconstructions from aerial images of disaster props",
abstract = "This paper provides a preliminary analysis of reconstructions of seven disaster props from datasets collected over five flights with a small unmanned aerial vehicle and finds 181 anomalies present in four categories. Commercial and free software are available to create reconstructions from digital images, but their accuracy and limitations have not been formally explored for disaster assessment. This work analyzes the output of two packages, Agisoft Photoscan, and Microsoft ICE for five image datasets of seven Disaster City{\circledR}props. The 181 anomalous results are divided into four categories: ghosting, misalignment, misproportions, and the Dali effect. These metrics are valuable to Urban Search and Rescue teams, structural specialists, and insurance claims adjusters who need to reliably assess whether it is safe to enter a building, or accurately estimate the severity of damage. The analysis suggests the reconstructions might be misleading and further work must be done to determine why and suggest methods of improvement.",
author = "Sarmiento, {Traci A.} and Duncan, {Brittany A} and Murphy, {Robin R.}",
year = "2016",
month = "3",
day = "29",
doi = "10.1109/SSRR.2015.7443004",
language = "English (US)",
series = "SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics",

}

TY - GEN

T1 - Preliminary analysis of reconstructions from aerial images of disaster props

AU - Sarmiento, Traci A.

AU - Duncan, Brittany A

AU - Murphy, Robin R.

PY - 2016/3/29

Y1 - 2016/3/29

N2 - This paper provides a preliminary analysis of reconstructions of seven disaster props from datasets collected over five flights with a small unmanned aerial vehicle and finds 181 anomalies present in four categories. Commercial and free software are available to create reconstructions from digital images, but their accuracy and limitations have not been formally explored for disaster assessment. This work analyzes the output of two packages, Agisoft Photoscan, and Microsoft ICE for five image datasets of seven Disaster City®props. The 181 anomalous results are divided into four categories: ghosting, misalignment, misproportions, and the Dali effect. These metrics are valuable to Urban Search and Rescue teams, structural specialists, and insurance claims adjusters who need to reliably assess whether it is safe to enter a building, or accurately estimate the severity of damage. The analysis suggests the reconstructions might be misleading and further work must be done to determine why and suggest methods of improvement.

AB - This paper provides a preliminary analysis of reconstructions of seven disaster props from datasets collected over five flights with a small unmanned aerial vehicle and finds 181 anomalies present in four categories. Commercial and free software are available to create reconstructions from digital images, but their accuracy and limitations have not been formally explored for disaster assessment. This work analyzes the output of two packages, Agisoft Photoscan, and Microsoft ICE for five image datasets of seven Disaster City®props. The 181 anomalous results are divided into four categories: ghosting, misalignment, misproportions, and the Dali effect. These metrics are valuable to Urban Search and Rescue teams, structural specialists, and insurance claims adjusters who need to reliably assess whether it is safe to enter a building, or accurately estimate the severity of damage. The analysis suggests the reconstructions might be misleading and further work must be done to determine why and suggest methods of improvement.

UR - http://www.scopus.com/inward/record.url?scp=84967019317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84967019317&partnerID=8YFLogxK

U2 - 10.1109/SSRR.2015.7443004

DO - 10.1109/SSRR.2015.7443004

M3 - Conference contribution

AN - SCOPUS:84967019317

T3 - SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics

BT - SSRR 2015 - 2015 IEEE International Symposium on Safety, Security, and Rescue Robotics

PB - Institute of Electrical and Electronics Engineers Inc.

ER -