James, Jasmin (Queensland University of Technology), Ford, Jason (Queensland University of Technology), Molloy, Timothy L. (Queensland University of Technology)

Below Horizon Aircraft Detection Using Deep Learning for Vision-Based Sense and Avoid

Scheduled for presentation during the Regular Session "See-and-avoid Systems" (ThC1), Thursday, June 13, 2019, 16:00−16:20, Heritage B

2020 International Conference on Unmanned Aircraft Systems (ICUAS), June 11-14, 2019, Athens, Greece

This information is tentative and subject to change. Compiled on April 18, 2024

Abstract

The commercial operation of unmanned aerial vehicles (UAVs) would benefit from an onboard capability to sense and avoid (SAA) potential mid-air collision threats in the same manner expected from a human pilot. In this paper we present a new approach for detection of aircraft below the horizon. We address some of the challenges faced by existing vision-based SAA methods such as detecting stationary aircraft (that have no relative motion to the background), rejecting moving ground vehicles, and simultaneous detection of multiple aircraft. We propose a multi-stage vision-based aircraft detection system which utilises deep learning to produce candidate aircraft that we track over time. We evaluate the performance of our proposed system on real flight data where we demonstrate detection ranges comparable to the state of the art with the additional capability of detecting stationary aircraft, rejecting moving ground vehicles, and tracking multiple aircraft.