Abstract
AbstractDue to complicated backgrounds and unclear target orientation, automated object detection is difficult in the field of archaeology. Most of the current convolutional neural network (CNN) object‐oriented detection techniques are based on a faster region‐based CNN (R‐CNN) and other one‐stage detectors that often lack adequate processing speeds and detection accuracies. Recently, the two‐stage detector Mask R‐CNN technique achieved impressive results in object detection and instance segmentation problems and was successfully applied in the analysis of archaeological airborne laser scanning (ALS) data. In this study, we outline a modified Mask R‐CNN technique that reliably and efficiently detects relict charcoal hearth (RCH) sites on light detection and ranging (LiDAR) data‐based digital elevation models (DEMs). Using image augmentation and image preprocessing steps combined with the deep learning‐based adaptive gradient method with a dynamic bound on the learning rate (AdaBound) optimization technique, we could improve the model's accuracy and significantly reduce its training time. We use DEMs based on high‐resolution LiDAR data and the visualization for archaeological topography (VAT) technique that give images with a very strong contrast of the terrain and the outline of the sites of interest in the North German Lowland. Therefore, the model can identify RCH sites with an average recall of 83% and an average precision of 87%. Techniques such as the modified Mask R‐CNN method outlined here will help to greatly improve our knowledge about archaeological site densities in the realm of historical charcoal production and past human‐landscape interactions. This method provides an accurate, time‐efficient and bias‐free large‐scale site mapping option not only for the North German Lowland but potentially for other landscapes as well.
Highlights
The increasing availability of airborne high-resolution light detection and ranging (LiDAR) data has led to an ever-growing interest in applying remote sensing to the archaeological domain, in which the use of machine learning techniques is increasing (e.g., Cowley et al, 2020; Davis, 2018; Opitz & Herrmann, 2018)
Mask R-convolutional neural network (CNN) has been used by Kazimi et al (2019) for the digital elevation models (DEMs)-based identification of archaeological objects such as bomb craters, charcoal hearths, and barrows, constituting a multiobject detection approach
We propose several modifications and extensions to the standard Mask region-based CNN (R-CNN) technique to (1) make it adapt easier to new data and reduce overfitting, (2) minimize the training time of the model and (3) improve the model's accuracy by adding image preprocessing and augmentation steps
Summary
The increasing availability of airborne high-resolution light detection and ranging (LiDAR) data has led to an ever-growing interest in applying remote sensing to the archaeological domain, in which the use of machine learning techniques is increasing (e.g., Cowley et al, 2020; Davis, 2018; Opitz & Herrmann, 2018). RCHs are generally circular in shape, with a wide range of diameters (up to 30 m and averaging 12 m), are elevated several decimetres above the earth's surface and are often surrounded by a shallow circular ditch or multiple small pits (Hirsch et al, 2020) These morphological properties are favourable for detecting RCHs on LiDAR-based digital elevation model (DEM). Mask R-CNN has been used by Kazimi et al (2019) for the DEM-based identification of archaeological objects such as bomb craters, charcoal hearths, and barrows, constituting a multiobject detection approach. We outline an improved method to detect charcoal hearths that can be applied to other objects in LiDAR DEMs. The study area is located in Lower Lusatia in the North German Lowland (Figure 1). The bounding boxes were drawn to include the platforms and the ditch DEM signature
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
