FIMD: Fast Isolated Marker Detection for UV-Based Visual Relative Localisation in Agile UAV Swarms

TL;DR

This paper introduces a rapid onboard marker detection system for visual relative localisation in UAV swarms, utilizing CPU, GPU, and FPGA implementations to achieve significant speed improvements for real-time applications.

Contribution

It presents a novel multi-platform detection approach with optimized CPU, GPU, and FPGA solutions, enabling fast and efficient UAV swarm localisation.

Findings

CPU and GPU processing times accelerated by 100-1000x

FPGA architecture minimized total delay for real-time detection

Demonstrated feasibility on low-end embedded platforms

Abstract

A novel approach for the fast onboard detection of isolated markers for visual relative localisation of multiple teammates in agile UAV swarms is introduced in this paper. As the detection forms a key component of real-time localisation systems, a three-fold innovation is presented, consisting of an optimised procedure for CPUs, a GPU shader program, and a functionally equivalent FPGA streaming architecture. For the proposed CPU and GPU solutions, the mean processing time per pixel of input camera frames was accelerated by two to three orders of magnitude compared to the \rev{unoptimised state-of-the-art approach}. For the localisation task, the proposed FPGA architecture offered the most significant overall acceleration by minimising the total delay from camera exposure to detection results. Additionally, the proposed solutions were evaluated on various 32-bit and 64-bit embedded platforms to demonstrate their efficiency, as well as their feasibility for applications using low-end UAVs and MAVs. Thus, it has become a crucial enabling technology for agile UAV swarming.