# A Novel Technique for Rejecting Non-Aircraft Artefacts in Above Horizon Vision-Based Aircraft Detection

## TL;DR

This paper introduces a new vision-based aircraft detection method that effectively reduces false alarms caused by clouds and terrain, improving detection range for UAV collision avoidance.

## Contribution

The novel technique models and penalizes non-aircraft artefacts, enhancing detection accuracy and range in complex visual environments.

## Key findings

- Achieved a mean detection range of 2445m at zero false alarms.
- Improved detection range by 9.8% compared to previous methods.
- Demonstrated effectiveness on real flight data with UAV and aircraft.

## Abstract

Unmanned aerial vehicle (UAV) operations are steadily expanding into many important applications. A key technology for better enabling their commercial use is an onboard sense and avoid (SAA) technology which can detect potential mid-air collision threats in the same manner expected from a human pilot. Ideally, aircraft should be detected as early as possible whilst maintaining a low false alarm rate, however, textured clouds and other unstructured terrain make this trade-off a challenge. In this paper we present a new technique for the modelling and detection of aircraft above the horizon that is able to penalise non-aircraft artefacts (such as textured clouds and other unstructured terrain). We evaluate the performance of our proposed system on flight data of a Cessna 172 on a near collision course encounter with a ScanEagle UAV data collection aircraft. By penalising non-aircraft artefacts we are able to demonstrate, for a zero false alarm rate, a mean detection range of 2445m corresponding to an improvement in detection ranges by 9.8% (218m).