Place Recognition in Forests with Urquhart Tessellations

TL;DR

This paper introduces a new forest place recognition method using Urquhart tessellations of tree positions, improving accuracy and robustness in UAV-based map merging tasks.

Contribution

The paper presents a novel descriptor based on Urquhart tessellations for forest place recognition, demonstrating superior performance over existing methods.

Findings

Outperforms state-of-the-art in accuracy

Effective with partial overlap and noise

Validated on UAV forest data

Abstract

In this letter, we present a novel descriptor based on Urquhart tessellations derived from the position of trees in a forest. We propose a framework that uses these descriptors to detect previously seen observations and landmark correspondences, even with partial overlap and noise. We run loop closure detection experiments in simulation and real-world data map-merging from different flights of an Unmanned Aerial Vehicle (UAV) in a pine tree forest and show that our method outperforms state-of-the-art approaches in accuracy and robustness.