Skip to content

JKU-ICG/AOS

Repository files navigation

AOS: Airborne Optical Sectioning

Airborne Optical Sectioning (AOS) is a wide synthetic-aperture imaging technique that employs manned or unmanned aircraft, to sample images within large (synthetic aperture) areas from above occluded volumes, such as forests. Based on the poses of the aircraft during capturing, these images are computationally combined to integral images by light-field technology. These integral images suppress strong occlusion and reveal targets that remain hidden in single recordings.

Single Images Airborne Optical Sectioning
single-images AOS

Source: Video on YouTube | FLIR

This repository contains software modules for drone-based search and rescue applications with airborne optical sectioning, as discussed in our publications. They are made available under a dual licence model.

Please refer to:

This research is supported by variaty of sponsors. See news for latest updates.

Contacts

Univ.-Prof. Dr. Ing. habil. Oliver Bimber

Johannes Kepler University Linz
Institute of Computer Graphics
Altenberger Straße 69
Computer Science Building
3rd Floor, Room 0302
4040 Linz, Austria

Phone: +43-732-2468-6631 (secretary: -6630)
Web: www.jku.at/cg
Email: oliver.bimber@jku.at

Sponsors and Collaborators

  • Austrian Science Funds (FWF)
  • German Science Funds (DFG)
  • State of Upper Austria (OÖ)
  • Nationalstiftung für Forschung, Technologie und Entwicklung (FTE)
  • Linz Institute of Technology (LIT)
  • German Aerospace Center (DLR)
  • Upper Austrian Fire Brigade Association (OÖLFV)
  • Federal Office of Metrology and Surveying (BEV)

News (see also Press)

  • 4/29/2024: First Field-Experiment with Drone Swarm: See AOS for Swarms and Air-to-Air Video Recording
  • 4/8/2024: AOS data sources summarized: See AOS Data
  • 3/19/2024: Waypoint planning for swarms: See AOS for Swarms
  • 3/8/2024: AOS on TV: Marys Magazin (ORF2, ARD Aplha).
  • 2/29/2024: Simulated AOS training data made available: See AOS Simulation
  • 2/14/2024: New image fusion approach presented (with first results on wildfire monitoring): See publications
  • 1/19/2024: Real-time map visualization of swarms: See AOS for Swarms
  • 12/25/2023: DL-based fusion of multispectral integral and single images: See publications
  • 11/9/2023: Stereoscopic AOS: First-person-view (FPV) stereoscopic AOS visualization supported for DJI (via stereoscopic HMDs attached to the remote controls).
  • 10/24/2023: New findings on stereoscopic depth perception through foliage: See publications
  • 10/31/2023: New research project AOSonFire started (early wildfire detection using AOS). Together with Upper Austrian Fire Brigade Headquarters.
  • 09/05/2023: Synthetic Aperture Anomaly Imaging published in J. Remote Sensing. See publications
  • 08/3/23: Behind-the-paper story of new Nature Com. Eng. article on AOS drone swarm strategies.
  • 06/01/23: Additional research grants for AOSonFire: Airborne Optical Sectioning for Early Wildfire Detection. In collaboration with Upper Austrian Fire Brigade Headquarters.
  • 05/25/23: Nature Communications Engineering paper accepted. See publications (Synthetic Aperture Sensing for Occlusion Removal with Drone Swarms)
  • 04/24/2023: AOS covered in April issues of Drones Magazin and Drohnen Magazin
  • 03/29/2023: AOS at AERO Drones. See AOS at AERODrones, Hall A2, Booth 113.
  • 03/01/2023: New Weave (FWF&DFG) funded basic research project on AOS for moving targets granted. In collaboration with German Aerospace Center (DLR) and Otto-von-Guericke University Magdeburg.
  • 02/08/2023: DJI SDK 5 support (Mavic 3T, etc.) and new app with real-time anomaly detection. See AOS for DJI
  • 12/30/2022: First AOS approach towards drone swarms for autonomous and adaptive sampling. See publications (Synthetic Aperture Sensing for Occlusion Removal with Drone Swarms)
  • 11/29/2022: Study on state-of-the-art color anomaly detectors suitable for through-foliage detection and tracking. See publications (Evaluation of Color Anomaly Detection in Multispectral Images For Synthetic Aperture Sensing)
  • 07/28/2022: Inverse Airborne Optical Sectioning -- through-foilage tracking with a single, conventional, hovering (stationary) drone. See publications (Inverse Airborne Optical Sectioning)
  • 06/13/2022: DJI Enterprise Systems with Thermal Imaging supported See AOS for DJI
  • 04/25/2022: Through-Foliage Tracking with Airborne Optical Sectioning pubisled in Science Partner Journal of Remote Sensing. See publications (Through-Foliage Tracking with Airborne Optical Sectioning)
  • 03/22/2022: AOS for DJI released See AOS for DJI
  • 03/09/2022: Combined Person Classification with Airborne Optical Sectioning published in Nature Scientific Reports
  • 11/29/2021: Our recent work, Acceleration-Aware Path Planning with Waypoints has been published. See publications (Acceleration-Aware Path Planning with Waypoints)
  • 06/23/2021: Science Robotics paper appeared. See publications (Autonomous Drones for Search and Rescue in Forests)
  • 5/31/2021: New combined people classifer outbeats classical people classifers significantly. See publications (Combined People Classification with Airborne Optical Sectioning)
  • 04/15/2021: First AOS experiments with DJI M300RTK reveals remarkable results (much better than with our OktoXL 6S12, due to higher GPS precission and better IR camera/stabilizer).

Publications

License

This repository contains software modules for drone-based search and rescue applications with airborne optical sectioning, as discussed in our publications. They are made available under a dual licence model.