Applying automated object detection in archaeological practice: A case study from the southern Netherlands

Abstract

Within archaeological prospection, Deep Learning algorithms are developed to detect objects within large remotely sensed datasets. These approaches are generally tested in an (ideal) experimental setting but have not been applied in different contexts or 'in the wild', that is, incorporated in archaeological prospection. This research explores the applicability, knowledge discovery-on both a quantitative and qualitative level-and efficiency gain resulting from employing an automated detection tool called WODAN within (Dutch) archaeological practice. WODAN has been used to detect barrows and Celtic fields in LiDAR data from the Dutch Midden-Limburg area, which differs in archaeology, geo-(morpho)logy and land-use from the Veluwe in which it was developed. The results show that WODAN was able to detect potential barrows and Celtic fields, including previously unknown examples, and provided information about the structuring of the landscape in the past. Based on the results, combined human-computer strategies are argued, in which automated detection has a complementary, rather than a substitute role, to manual analysis. This can offset the inherent biases in manual analysis and deal with the problem that current automated detection methods only detect objects similar to the pre-defined target class(es). The incorporation of automated detection into archaeological prospection, in which the results of automated detection are used to highlight areas of interest and to enhance and add detail to existing archaeological predictive maps, seems logical and feasible.

Comparing geomorphological maps made manually and by deep learning

“…This is a more common find in studies that try to detect landforms with deep learning (e.g. Verschoof‐Van der Vaart & Lambers, 2021). Before CNNs can (partly) take over the work of manual mappers in creating geomorphological maps and become part of the workflow for geomorphological mapping, more development and testing of the models, parameters and input is required.…”

“…At this stage, semi-automated mapping with CNNs can be seen as an additional tool in the mapping process, as the computed maps can identify areas that are ambiguously defined or may spark the discussion of classification definitions, scale issues and landform dominance. This is a more common find in studies that try to detect landforms with deep learning (e.g Verschoof-Van der Vaart & Lambers, 2021)…”

Lidar visualization techniques for the construction of geoarchaeological deposit models: An overview and evaluation in alluvial environments

“…Beyond increasing image contrast for the human perception of archaeological features and natural landforms, lidar visualizations are also utilized to improve automated, or semiautomated, object detection (Davis, 2019;Verschoof-van der Vaart & Lambers, 2022).…”

“…Beyond increasing image contrast for the human perception of archaeological features and natural landforms, lidar visualizations are also utilized to improve automated, or semiautomated, object detection (Davis, 2019; Verschoof‐van der Vaart & Lambers, 2022). In geomorphology, these procedures are increasingly critical for providing a quantification and recognition of landforms that possess unique morphometric characteristics (Evans, 2012; Jasiewicz & Stepinski, 2013; Lin et al, 2021; Wang et al, 2010).…”

GPR Data Processing and Interpretation Based on Artificial Intelligence Approaches: Future Perspectives for Archaeological Prospection

“…It has experimented with geospatial data/images (satellite, aerial, lidar), texts, categorical tableau data, point clouds, and other datasets. For instance, one can consider some indicative examples such as the work that has been done on bone classification [1], remote sensing archaeology [2][3][4][5][6][7][8][9][10][11][12], geophysical prospection [13][14][15][16][17], detection of objects in paintings [18], classification of pottery [19], and the 3D reconstruction of heritage buildings [20]. The main reason behind this growing trend, which has been noticed in the last five years in all scientific domains, underlies the nuisance generated when dealing with multivariate analysis of high-volume datasets, which are challenging to process and interpret.…”