Using deep neural networks on airborne laser scanning data: Results from a case study of semi‐automatic mapping of archaeological topography on Arran, Scotland

Abstract

This article presents results of a case study within a project that seeks to develop heavily automated analysis of digital topographic data to extract archaeological information and to expedite large area mapping. Drawing on developments in computer vision and machine learning, this has the potential to fundamentally recast the capacity of archaeological prospection to cover large areas and deal with mass data, breaking a dependency on human resource. Without such developments, the potential of the vast amount of archaeological information embedded in large topographic and image-based datasets cannot be realized. The purpose of the case study reported on here is to assess existing developments in a Norwegian study against digital topographic data for the island of Arran, Scotland, examining the transferability of the approach and providing a proof of concept in a Scottish context. For Arran, three monument classes were assessedprehistoric roundhouses, shieling huts of medieval or post-medieval date, and small clearance cairns. These present different challenges to detection, with preliminary results ranging from a manageable mix of false positives and true identifications to the chaotic. The influence of variable morphology and the occurrence of other, largely natural, objects of confusion in the landscape is discussed, highlighting the potential improvements in automated detection routines offered by adding anthropogenic and natural false positives to additional confusion classes.

Identifying Linear Traces of the Han Dynasty Great Wall in Dunhuang Using Gaofen-1 Satellite Remote Sensing Imagery and the Hough Transform

“…This means that it is still necessary to intervene manually, which requires a lot of time, manpower and material resources [53][54][55]. With the rapid development of image and signal processing and computer vision, several (semi-) automatic approaches have also been designed for and applied to archaeological research [56][57][58][59][60]. For instance, Lasaponara et al [55] designed a classification-based semi-automatic approach for identifying four buried farm objects at the Hierapolis site; the identification results were then qualitatively evaluated by combining visual interpretation with the GPR survey data.…”

Searching for Viking Age Fortresses with Automatic Landscape Classification and Feature Detection

“…Automatic feature detection approaches for archaeology are a rapidly and fast developing field in archaeological prospection [60][61][62]. Recent studies have demonstrated machine learning methods for detecting a wide variety of features, including burial mounds, charcoal kilns, buildings, and field systems [10,[63][64][65][66].…”

“…Our automatic approach is, hence, adaptable to search for a wide variety of circular surface structures where digital elevation models (DEMs) are available. Such future studies could focus on common geomorphological features such as meandering rivers, coastal erosion scars, and glacial landforms [10,42,82], but also remote mapping of impact craters from meteors [57], bomb craters [83], and center pivot irrigation [84]. It may be even applicable on extra-terrestrial bodies [85].…”

“…This presents a difficult problem for feature detection approaches of remote sensing, where a large number of examples are usually used to train classifiers [10][11][12][13][14][15]. In this case, these methods are inappropriate, as Borgring is the only example of an erosion damaged fortress that has not been extensively reconstructed in the recent past [16].…”

Deep learning based automated analysis of archaeo‐geophysical images

“…The main interest however, has been focused mainly on the analysis of archaeological features from airborne laser scanning (ALS) and satellite data. Such applications have been summarized by Trier, Cowley, and Waldeland (), Opitz and Herrmann (), Davis (), and Davis, Lipo, and Sanger (); and the recent studies of Verschoof‐van, der Vaart, and Lambers (), Meyer, Pfeffer, and Jürgens (), and Lambers, Verschoof‐van der Vaart, and Bourgeois (). Automated analysis is also considered to be an important approach for ground‐based geophysical surveys.…”