Although the history of automated archaeological object detection in remotely sensed data is short, progress and emerging trends are evident. Among them, the shift from rule-based approaches... Show moreAlthough the history of automated archaeological object detection in remotely sensed data is short, progress and emerging trends are evident. Among them, the shift from rule-based approaches towards machine learning methods is, at the moment, the cause for high expectations, even though basic problems, such as the lack of suitable archaeological training data are only beginning to be addressed. In a case study in the central Netherlands, we are currently developing novel methods for multi-class archaeological object detection in LiDAR data based on convolutional neural networks (CNNs). This research is embedded in a long-term investigation of the prehistoric landscape of our study region. We here present an innovative integrated workflow that combines machine learning approaches to automated object detection in remotely sensed data with a two-tier citizen science project that allows us to generate and validate detections of hitherto unknown archaeological objects, thereby contributing to the creation of reliable, labeled archaeological training datasets. We motivate our methodological choices in the light of current trends in archaeological prospection, remote sensing, machine learning, and citizen science, and present the first results of the implementation of the workflow in our research area. Show less
Since 2007, the Silvretta Archaeological Project in the high Alps on the Swiss-Austrian border has been investigating the prehistoric origins of alpine pasture economy. In an area of about 540 km2... Show moreSince 2007, the Silvretta Archaeological Project in the high Alps on the Swiss-Austrian border has been investigating the prehistoric origins of alpine pasture economy. In an area of about 540 km2 more than 20 well-preserved archaeological sites associated with alpine pastoralism have been recorded, the earliest of them dating to the Iron Age (Reitmaier (ed.), 2012; Walser and Lambers, 2012). All of the ruined huts, cellars and livestock enclosures at these sites are visible on the surface and show a limited range of shapes and proportions. According to their function, all of them are located in open grassland. Based on this sample, we are currently developing methods to detect archaeological objects of the kind described above in high-resolution satellite images of our study area (Lambers and Zingman, in press). These methods are intended to assist archaeological survey in vast and/or difficult to access areas by screening large amounts of remotely sensed images in order to detect possible archaeological sites prior to fieldwork (Cowley, 2012). Our general approach aims at assessing the probability of the presence of objects of our interest based on geometric cues that can be automatically detected in the satellite and aerial images that we use. We here describe our general methodology and the first integral step constituting a new approach to texture segmentation. Show less
