Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Jincheng, Ringle, William, Willis, Andrew R.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.05773
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910361256460288
author Zhang, Jincheng
Ringle, William
Willis, Andrew R.
author_facet Zhang, Jincheng
Ringle, William
Willis, Andrew R.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_05773
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unveiling Ancient Maya Settlements Using Aerial LiDAR Image Segmentation
Zhang, Jincheng
Ringle, William
Willis, Andrew R.
Computer Vision and Pattern Recognition
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.
title Unveiling Ancient Maya Settlements Using Aerial LiDAR Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.05773