Drones That Can See Around Trees With Thermal – Code Available

I previously interviewed Oliver Bimber regarding his work with Airborne Optical Sectioning.

This software solution allows drones to fly autonomously and using AI it can piece together glimpses of thermal responses and then identify those that are humans below tree canopies.

It is a revolutionary piece of software and when drones that are authorized to fly long and further become available, this software could radically change how we find missing people under trees.

According to Oliver Bimber, “after the publication of our new Science Robotics paper today, we are making available our documented source code on Airborne Optical Sectioning (AOS).

This repository contains software modules and data for drone-based search and rescue applications with AOS, as discussed in our publications (which are also accessible through the repository). All source code is made available under a dual license model (free for non-commercial usage and individual licenses for commercial usage).

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.”