Heidelberg University
Institute of Geography logo

Research LOKI

Airborne Observation of Critical Infrastructures

Luftgestützte Observation Kritischer Infrastrukturen

LOKI Logo

General information

A full overview and detailed description of the LOKI project and the functionality of the developed modules is explained in the extensive LOKI Wiki. Code of the modules developed in LOKI is hosted and documented on GitLab.

  • Funding: Federal Ministry for Education and Research (BMBF),
    • Funding code: 03G0890A
    • Funding priority: Früherkennung von Erdbeben und ihren Folgen
  • Duration: 2020 - 2023
  • Project coordinator: Prof. Bernhard Höfle, Insitute of Geography, Heidelberg University
  • Project partners:
    • Heidelberg University: Prof. Bernhard Höfle, Prof. Alexander Zipf
    • Aeromey GmbH: Heiko Mey
    • FZI Research Center for Information Technology: Dr. Katharina Glock
    • German Research Center for Geoscience (GFZ): Dr. Danijel Schorlemmer
    • Karlsruhe Institute of Technology (KIT): Prof. Lothar Stempniewski

News

Find latest project updates in the “Stories” chapter of our LOKI GitLab Wiki.
Follow further project updates on X/Twitter: #LOKI #BMBF.

Final project report:

  • Zahs, V., Kohns, J., Meyer, F., Schorlemmer, D., Anders, K., Klonner, C., Mey, H., Oostwegel, L., Zadeh, T. & Höfle, B. (2023): LOKI – Luftgestützte Observation Kritischer Infrastrukturen. Schlussbericht. Ruprecht-Karls-Universität Heidelberg, 120 S. DOI: 10.2314/KXP:1885697937.

Motivation

The aim of the LOKI project is to develop an interdisciplinary system that enables fast and reliable airborne situation assessments following an earthquake. The system will serve to reduce longer-term damage after an earthquake by recording information on the current situation as efficiently as possible, thereby enabling remediation actions to be undertaken within appropriate timescales. A central focus is the timely overview and detailed recording of the damage to critical infrastructures, such as lifelines (bridges and roads), health care facilities and public institutions (e.g. schools). LOKI will improve the response time and reliability of information provided in the event of an earthquake, and enables better use of existing resources and emergency forces. The objectives will be met by combining existing expertise in earthquake research with a variety of new technologies and concepts, including machine learning, crowdsourcing, Unmanned Aerial Vehicles (UAVs, flying drones available for civil use) and 3D monitoring.

Workflow of the LOKI Project

Project partners and their research focuses in the project

Heidelberg University serves as the coordinator of the research project, which is a collaboration between several project partners. Within this collaboration, components and services developed by the individual partners will be integrated into a single system.

Table

UHD Logo

Automatic damage detection: In order to determine the relevance of the detected damage, methods will be developed to combine:

  • image-based damage detection with 3D geometric damage detection.
  • machine learning with visual (semantic) interpretation by crowdsourcing.

Crowdsourcing and user-generated geoinformation: Methods developed for:

  • (3D) Micro-Mapping for damage mapping and evaluation of the generated information.
  • determining the influencing factors and the optimal combination with automatic, computer-based damage detection.
Aeromey Logo

Aeromey GmbH

UAV-Infrastructure: Development of an ad-hoc network among UAVs, for smooth and fast communication even over longer distances.

FZI Logo

FZI Research Center for Information Technology

Coordination mechanisms for UAV fleets: Coordination mechanisms for UAV fleets: Development of real-time capable and adaptive planning mechanisms for UAVs and investigation of decentralized coordination mechanisms, with which UAVs themselves coordinate the division of the area, the prioritization of targets and the route to be flown.

GFZ Logo

German Research Center for Geoscience (GFZ)

Exposure modelling: Integration of crowdsourcing and primary UAV overflights into building-specific (iterative) exposure modelling, as well as the adaptation of corresponding evaluation algorithms. This approach is capable of working with very heterogeneous data availability.

KIT Logo

Karlsruhe Institute of Technology (KIT)

Earthquake engineering for damage classification: Development of damage interpretation rules and decision criteria for (semi-)automatic damage assessment using UAV flying and crowdsourcing.

Project Video

Collaboration partners

Table

Earthquake Research Institute
University of Tokyo, Japan
Institute of Geophysics
National Central University (NCU), Taiwan
Department of Geomatics
National Cheng Kung University (NCKU), Taiwan
Dipartimento di Scienze della Terra, dell’Ambiente e delle Risorse (DiSTAR)
Università di Napoli Federico II, Italy
Kathmandu Living Labs, Nepal
Arbeiter-Samariter-Bund Mannheim
Branddirektion Karlsruhe
Deutsches Rotes Kreuz Berlin
Feuerwehr Heidelberg
Technisches Hilfswerk Heidelberg

Publications

Table

Zahs, V., Kohns, J., Meyer, F., Schorlemmer, D., Anders, K., Klonner, C., Mey, H., Oostwegel, L., Zadeh, T. & Höfle, B. (2023): LOKI – Luftgestützte Observation Kritischer Infrastrukturen. Schlussbericht. Ruprecht-Karls-Universität Heidelberg, 120 S. DOI: 10.2314/KXP:1885697937.
Zahs, V., Anders, K., Kohns, J., Stark, A. & Höfle, B. (2023): Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data.International Journal of Applied Earth Observation and Geoinformation. Vol. 122, pp. 103406. DOI: 10.1016/j.jag.2023.103406
Zahs, V., Anders, K., Kohns, J., Stark, A. & Höfle, B. (2023): Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data [Data and Source Code]. heiDATA. DOI: 10.11588/data/D3WZID
Ullah, T., Lautenbach, S., Herfort, B., Schorlemmer, D. (2023): Assessing Completeness of OpenStreetMap Building Footprints Using a Gamification Approach in MapSwipe. Preprints 2023, 2023010550. DOI: 0.20944/preprints202301.0550.v1
Zahs, V., Anders, K., Kohns, J., Stark, A. & Höfle, B. (2023): Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data. arXiv:2302.12591 [cs.CV]. DOI: 10.48550/arXiv.2302.12591
Kohns, J., Stempniewski, L. & Stark, A. (2022): Fragility Functions for Reinforced Concrete Structures Based on Multiscale Approach for Earthquake Damage Criteria. Buildings. Vol. 12(08), pp. 1-17. DOI: 10.3390/buildings12081253
Kohns, J., Stempniewski, L. & Stark, A. (2022): Entwicklung von Schadenskatalogen für die visuelle Beurteilung von Gebäuden im Erdbebenfall. Bauingenieur, Vol. 12, pp. 403-412.
Kohns, J., Stempniewski, L. & Stark, A. (2022): Earthquake damage criteria for non-linear analysis of reinforced concrete buildings as basis for fragility functions. Proceedings of the 3rd European Conference on Earthquake Engineering & Seismology, Bucharest, Romania, pp. 1646-1653.
Meyer, F. & Glock, K. (2022): Kinematic Orienteering Problem With Time-Optimal Trajectories for Multirotor UAVs. IEEE Robotics and Automation Letters. Vol. 7(4), pp. 11402-11409. DOI: doi: 10.1109/LRA.2022.3194688.
Winiwarter, L., Esmorís Pena, A. M., Zahs, V., Weiser, H., Searle, M., Anders, K., & Höfle, B. (2022): Virtual Laser Scanning using HELIOS++ - Applications in Machine Learning and Forestry. EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022. DOI: 10.5194/egusphere-egu22-8671.
Winiwarter, L., Esmorís Pena, A., Weiser, H., Anders, K., Martínez Sanchez, J., Searle, M. & Höfle, B. (2022): Virtual laser scanning with HELIOS++: A novel take on ray tracing-based simulation of topographic full-waveform 3D laser scanning. Remote Sensing of Environment. Vol. 269. DOI: 10.1016/j.rse.2021.112772.
Zahs, V., Winiwarter, L., Anders, K., Williams, J.G., Rutzinger, M. & Höfle, B. (2022): Correspondence-driven plane-based M3C2 for lower uncertainty in 3D topographic change quantification. ISPRS Journal of Photogrammetry and Remote Sensing. Vol. 183, pp. 541-559. DOI: 10.1016/j.isprsjprs.2021.11.018.
Zahs, V., Winiwarter, L., Anders, K., Williams, J.G., Rutzinger, M. & Höfle, B. (2022): Correspondence-driven plane-based M3C2 for lower uncertainty in 3D topographic change quantification [Data and Source Code]. heiDATA. DOI: 10.11588/data/TGSVUI.
Kohns, J. & Stempniewski, L. (2021): Classification of earthquake-induced building damage using innovative methods. IABSE Congress Ghent 2021, pp. 1366–1374.
Kohns, J. & Stempniewski, L. (2021): Entwicklung von Schadenskriterien für nichtlineare Erdbebenuntersuchungen an Stahlbeton- und Mauerwerksgebäuden. Tagungsband zur 17. D-A-CH-Tagung Erdbebeningenieurwesen und Baudynamik, pp. 101-102.
Kohns, J., Zahs, V., Ullah, T., Schorlemmer, D., Nievas, C., Glock, K., Meyer, F., Mey, H., Stempniewski, L., Herfort, B., Zipf, A. & Höfle, B. (2021): Innovative methods for earthquake damage detection and classification using airborne observation of critical infrastructures (project LOKI). In: EGU General Assembly 2021. Vol. EGU21 (EGU21-2712), pp. 1-2. DOI: 10.5194/egusphere-egu21-2712.
Meyer, F. & Glock, K. (2021): Trajectory-based Traveling Salesman Problem for Multirotor UAVs. 17th International Conference on Distributed Computing in Sensor Systems (DCOSS), pp. 335-342. DOI: 10.1109/DCOSS52077.2021.00061.
Zahs, V., Herfort, B., Kohns, J., Ullah, T., Anders, K., Stempniewski, L., Zipf, A. & Höfle, B. (2021): 3D point cloud-based assessment of detailed building damage through a combination of machine learning, crowdsourcing and earthquake engineering. In: EGU General Assembly 2021. Vol. EGU21 (EGU21-1304), pp. 1-2. DOI: 10.5194/egusphere-egu21-1304.

Deutsch

Contact