Place Recognition in Forests With Urquhart Tessellations

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