UAV-borne remote sensing for AI-assisted support of search and rescue missions

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Reinhold Herschel
  • Patrick Wallrath
  • Michael Hofstätter
  • Philipp Taupe
  • Emily Krüger
  • Martina Philippi
  • Julian Kunze
  • Jan Michel Rotter
  • Victoria Heusinger
  • Meral Ari
  • René Kastner
  • Astrid Al-Akrawi

Research Organisations

External Research Organisations

  • Fraunhofer Institute for High Frequency Physics and Radar Techniques FHR
  • AIT Austrian of Institute of Technology GmbH
  • Bundesanstalt Technisches Hilfswerk (THW)
  • Ruhr-Universität Bochum
  • Fraunhofer Institute for High-Speed Dynamics, Ernst Mach Institute (EMI)
  • Disaster Competence Network Austria (DCNA)
View graph of relations

Details

Original languageEnglish
Title of host publicationElectro-Optical Remote Sensing XVI
EditorsGary W. Kamerman, Ove Steinvall
PublisherSPIE
ISBN (electronic)9781510655478
Publication statusPublished - 2 Nov 2022

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12272
ISSN (Print)0277-786X
ISSN (electronic)1996-756X

Abstract

In search and rescue (SAR) missions every minute counts. Semi-collapsed buildings are among the difficult scenarios encountered by search and rescue teams. An UAV-based exploration system can provide crucial information on the accessibility of different sectors, hazards, and injured people. The research project “UAV-Rescue” aims to provide UAV-borne sensing and investigate the use of AI to support this powerful tool. The sensor suite contains a radar sensor for detecting people based on breath and pulse movement. A neural network interprets the extracted data to identify signs of human life and as such persons that need rescuing. We also fuse radar and lidar data to explore the environment of the UAV and obtain a robust basis for simultaneous localization and mapping even under restricted visibility conditions. Additionally, we plan to use AI to support the path planning of the drone taking the digital map as input. Furthermore, AI is leveraged to map intact and damaged building structures. Potentially hazardous gases common to urban settings are tracked. We fuse the acquired information into a model of the explored area with marked locations of potential hazards and people to be rescued. The project also addresses ethical and societal issues raised by the use of UAVs close to people as well as AI supported decision making. The talk will present the system concept including interfaces and sensor fusion approaches. We will show first results of a research project from static and dynamic measurement campaigns demonstrating the capability of radar and lidar based sensing in a complex urban environment.

Keywords

    Radar, Unmanned aerial vehicles, Sensors, LIDAR, Artificial intelligence, Buildings, Legal, search and rescue, vital signs, DNN, AI, UAV, radar, lidar, 3D mapping

ASJC Scopus subject areas

Cite this

UAV-borne remote sensing for AI-assisted support of search and rescue missions. / Herschel, Reinhold; Wallrath, Patrick; Hofstätter, Michael et al.
Electro-Optical Remote Sensing XVI. ed. / Gary W. Kamerman; Ove Steinvall. SPIE, 2022. 1227203 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12272).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Herschel, R, Wallrath, P, Hofstätter, M, Taupe, P, Krüger, E, Philippi, M, Kunze, J, Rotter, JM, Heusinger, V, Ari, M, Kastner, R & Al-Akrawi, A 2022, UAV-borne remote sensing for AI-assisted support of search and rescue missions. in GW Kamerman & O Steinvall (eds), Electro-Optical Remote Sensing XVI., 1227203, Proceedings of SPIE - The International Society for Optical Engineering, vol. 12272, SPIE. https://doi.org/10.1117/12.2636032
Herschel, R., Wallrath, P., Hofstätter, M., Taupe, P., Krüger, E., Philippi, M., Kunze, J., Rotter, J. M., Heusinger, V., Ari, M., Kastner, R., & Al-Akrawi, A. (2022). UAV-borne remote sensing for AI-assisted support of search and rescue missions. In G. W. Kamerman, & O. Steinvall (Eds.), Electro-Optical Remote Sensing XVI Article 1227203 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12272). SPIE. https://doi.org/10.1117/12.2636032
Herschel R, Wallrath P, Hofstätter M, Taupe P, Krüger E, Philippi M et al. UAV-borne remote sensing for AI-assisted support of search and rescue missions. In Kamerman GW, Steinvall O, editors, Electro-Optical Remote Sensing XVI. SPIE. 2022. 1227203. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2636032
Herschel, Reinhold ; Wallrath, Patrick ; Hofstätter, Michael et al. / UAV-borne remote sensing for AI-assisted support of search and rescue missions. Electro-Optical Remote Sensing XVI. editor / Gary W. Kamerman ; Ove Steinvall. SPIE, 2022. (Proceedings of SPIE - The International Society for Optical Engineering).
Download
@inproceedings{fac96b0094904d42925d1e29fae3b8f7,
title = "UAV-borne remote sensing for AI-assisted support of search and rescue missions",
abstract = "In search and rescue (SAR) missions every minute counts. Semi-collapsed buildings are among the difficult scenarios encountered by search and rescue teams. An UAV-based exploration system can provide crucial information on the accessibility of different sectors, hazards, and injured people. The research project “UAV-Rescue” aims to provide UAV-borne sensing and investigate the use of AI to support this powerful tool. The sensor suite contains a radar sensor for detecting people based on breath and pulse movement. A neural network interprets the extracted data to identify signs of human life and as such persons that need rescuing. We also fuse radar and lidar data to explore the environment of the UAV and obtain a robust basis for simultaneous localization and mapping even under restricted visibility conditions. Additionally, we plan to use AI to support the path planning of the drone taking the digital map as input. Furthermore, AI is leveraged to map intact and damaged building structures. Potentially hazardous gases common to urban settings are tracked. We fuse the acquired information into a model of the explored area with marked locations of potential hazards and people to be rescued. The project also addresses ethical and societal issues raised by the use of UAVs close to people as well as AI supported decision making. The talk will present the system concept including interfaces and sensor fusion approaches. We will show first results of a research project from static and dynamic measurement campaigns demonstrating the capability of radar and lidar based sensing in a complex urban environment.",
keywords = "Radar, Unmanned aerial vehicles, Sensors, LIDAR, Artificial intelligence, Buildings, Legal, search and rescue, vital signs, DNN, AI, UAV, radar, lidar, 3D mapping",
author = "Reinhold Herschel and Patrick Wallrath and Michael Hofst{\"a}tter and Philipp Taupe and Emily Kr{\"u}ger and Martina Philippi and Julian Kunze and Rotter, {Jan Michel} and Victoria Heusinger and Meral Ari and Ren{\'e} Kastner and Astrid Al-Akrawi",
note = "Funding Information: We want to thank the German Ministry Federal for Education and Research for funding the German part of UAV-Rescue within the federal government framework program Research for Civil Security. The Austrian part of UAV-Rescue is funded by the Austrian security research program KIRAS of the Federal Ministry of Agriculture, Regions and Tourism.",
year = "2022",
month = nov,
day = "2",
doi = "10.1117/12.2636032",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Kamerman, {Gary W.} and Ove Steinvall",
booktitle = "Electro-Optical Remote Sensing XVI",
address = "United States",

}

Download

TY - GEN

T1 - UAV-borne remote sensing for AI-assisted support of search and rescue missions

AU - Herschel, Reinhold

AU - Wallrath, Patrick

AU - Hofstätter, Michael

AU - Taupe, Philipp

AU - Krüger, Emily

AU - Philippi, Martina

AU - Kunze, Julian

AU - Rotter, Jan Michel

AU - Heusinger, Victoria

AU - Ari, Meral

AU - Kastner, René

AU - Al-Akrawi, Astrid

N1 - Funding Information: We want to thank the German Ministry Federal for Education and Research for funding the German part of UAV-Rescue within the federal government framework program Research for Civil Security. The Austrian part of UAV-Rescue is funded by the Austrian security research program KIRAS of the Federal Ministry of Agriculture, Regions and Tourism.

PY - 2022/11/2

Y1 - 2022/11/2

N2 - In search and rescue (SAR) missions every minute counts. Semi-collapsed buildings are among the difficult scenarios encountered by search and rescue teams. An UAV-based exploration system can provide crucial information on the accessibility of different sectors, hazards, and injured people. The research project “UAV-Rescue” aims to provide UAV-borne sensing and investigate the use of AI to support this powerful tool. The sensor suite contains a radar sensor for detecting people based on breath and pulse movement. A neural network interprets the extracted data to identify signs of human life and as such persons that need rescuing. We also fuse radar and lidar data to explore the environment of the UAV and obtain a robust basis for simultaneous localization and mapping even under restricted visibility conditions. Additionally, we plan to use AI to support the path planning of the drone taking the digital map as input. Furthermore, AI is leveraged to map intact and damaged building structures. Potentially hazardous gases common to urban settings are tracked. We fuse the acquired information into a model of the explored area with marked locations of potential hazards and people to be rescued. The project also addresses ethical and societal issues raised by the use of UAVs close to people as well as AI supported decision making. The talk will present the system concept including interfaces and sensor fusion approaches. We will show first results of a research project from static and dynamic measurement campaigns demonstrating the capability of radar and lidar based sensing in a complex urban environment.

AB - In search and rescue (SAR) missions every minute counts. Semi-collapsed buildings are among the difficult scenarios encountered by search and rescue teams. An UAV-based exploration system can provide crucial information on the accessibility of different sectors, hazards, and injured people. The research project “UAV-Rescue” aims to provide UAV-borne sensing and investigate the use of AI to support this powerful tool. The sensor suite contains a radar sensor for detecting people based on breath and pulse movement. A neural network interprets the extracted data to identify signs of human life and as such persons that need rescuing. We also fuse radar and lidar data to explore the environment of the UAV and obtain a robust basis for simultaneous localization and mapping even under restricted visibility conditions. Additionally, we plan to use AI to support the path planning of the drone taking the digital map as input. Furthermore, AI is leveraged to map intact and damaged building structures. Potentially hazardous gases common to urban settings are tracked. We fuse the acquired information into a model of the explored area with marked locations of potential hazards and people to be rescued. The project also addresses ethical and societal issues raised by the use of UAVs close to people as well as AI supported decision making. The talk will present the system concept including interfaces and sensor fusion approaches. We will show first results of a research project from static and dynamic measurement campaigns demonstrating the capability of radar and lidar based sensing in a complex urban environment.

KW - Radar

KW - Unmanned aerial vehicles

KW - Sensors

KW - LIDAR

KW - Artificial intelligence

KW - Buildings

KW - Legal

KW - search and rescue

KW - vital signs

KW - DNN

KW - AI

KW - UAV

KW - radar

KW - lidar

KW - 3D mapping

UR - http://www.scopus.com/inward/record.url?scp=85145436526&partnerID=8YFLogxK

U2 - 10.1117/12.2636032

DO - 10.1117/12.2636032

M3 - Conference contribution

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Electro-Optical Remote Sensing XVI

A2 - Kamerman, Gary W.

A2 - Steinvall, Ove

PB - SPIE

ER -

By the same author(s)