Detection of aircraft below the horizon for vision‐based detect and avoid in unmanned aircraft systems

Abstract

Vision‐based aircraft detection technology may provide a credible sensing option for automated detect and avoid in small‐to‐medium size fixed‐wing unmanned aircraft systems (UAS). Reliable vision‐based aircraft detection has previously been demonstrated in sky‐region sensing environments. This paper describes a novel vision‐based system for detecting aircraft below the horizon in the presence of ground clutter. We examine the performance of our system on a data set of 63 near collision encounters we collected between a camera‐equipped manned aircraft and a below‐horizon target. In these 63 encounters, our system successfully detects all aircraft, at an average detection range of 1890 m (with a standard error of 43 m and no false alarms in 1.1 h). Furthermore, our system does not require access to inertial sensor data (which significantly reduces system cost) and operates at over 12 frames per second.

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

“…In this section we describe the flight experiments that we used to evaluate the performance of our proposed system. These experiments were conducted using the same aircraft and setup as described in [8] (and in the above training and labelling section). We examined a variety of different image sequences to characterise our proposed system including:…”

“…1) Head-on Encounters (T1-T10): We used cases 1 − 10 of the head-on, near collision course encounters presented in [8].…”

“…Detection of aircraft below the horizon presents new challenges as the environments are complex and cluttered as seen in Figure 1. The most successful approaches for below horizon visionbased aircraft detection exploit a multi-stage detection pipeline of image pre-processing and temporal filtering as seen in Figure 2 [4], [6], [8]. The image pre-processing stage aims to extract potential aircraft in an image.…”

“…The image pre-processing stage aims to extract potential aircraft in an image. The dominant approach is to use frame differencing (or background subtraction) to extract potential aircraft that have apparent motion with respect to the background [4], [6], [8]. The temporal filtering stage aims to track these potential aircraft in an image sequence.…”

“…Moreover, the majority of these approaches have been adapted from detecting moving ground vehicles, and hence struggle to reject this type of false alarm [8]. Finally, the detection system of [8] is for a single aircraft and does not detect multiple aircraft threats. In this paper we propose a system to address these concerns by exploiting aircraft visual appearance rather than relying on apparent motion with respect to the background.…”