Unveiling Ancient Maya Settlements Using Aerial LiDAR Image Segmentation

TL;DR

This paper demonstrates how deep learning, specifically YOLOv8, can automate and improve the segmentation of ancient Maya archaeological features in aerial LiDAR images, surpassing existing methods.

Contribution

It introduces a novel pre-processing and dataset augmentation approach for YOLOv8 to enhance archaeological feature segmentation accuracy.

Findings

IoU of 0.842 for platforms

IoU of 0.809 for annular structures

Outperforms existing segmentation methods

Abstract

Manual identification of archaeological features in LiDAR imagery is labor-intensive, costly, and requires archaeological expertise. This paper shows how recent advancements in deep learning (DL) present efficient solutions for accurately segmenting archaeological structures in aerial LiDAR images using the YOLOv8 neural network. The proposed approach uses novel pre-processing of the raw LiDAR data and dataset augmentation methods to produce trained YOLOv8 networks to improve accuracy, precision, and recall for the segmentation of two important Maya structure types: annular structures and platforms. The results show an IoU performance of 0.842 for platforms and 0.809 for annular structures which outperform existing approaches. Further, analysis via domain experts considers the topological consistency of segmented regions and performance vs. area providing important insights. The approach automates time-consuming LiDAR image labeling which significantly accelerates accurate analysis of historical landscapes.