In contrast with the understanding of present-day soil erosion processes, knowledge on past soil erosion phenomena is still rather limited. Although some studies report on severe gully erosion phases during the fourteenth and eighteenth centuries, almost no evidence is available that documents earlier gully erosion phases. This study investigates the development and age of two old, permanent gullies that are conserved in the ancient Meerdaal forest in central Belgium. The development history of both gullies is very similar. In the first gully, archaeological evidence was found indicating an erosion phase during Roman times, followed by a partial infilling of the gully. In the second gully, radiocarbon dating provided evidence of the same Roman activity phase (cal. yr 46 BC-AD 78), but also of an earlier incision phase during the Middle Bronze Age (cal. yr 1743-1602, 1568-1533 BC). Also here, the erosion phase was followed by a partial infilling. This limited infilling indicates that the catchment of the gullies was reforested quite rapidly, hereby cutting off all runoff and sediment production. This has led to a unique situation in the Meerdaal forest, with the conservation of about 43 similar, large gullies in an area of about 17 km2. This area has a high geovalue, as the studied gullies are among the oldest and best conserved gullies in northwestern Europe.
The accurate detection of cracks in paintings, which generally portray rich and varying content, is a challenging task. Traditional crack detection methods are often lacking on recent acquisitions of paintings as they are poorly adapted to high-resolutions and do not make use of the other imaging modalities often at hand. Furthermore, many paintings portray a complex or cluttered composition, significantly complicating a precise detection of cracks when using only photographic material. In this paper, we propose a fast crack detection algorithm based on deep convolutional neural networks (CNN) that is capable of combining several imaging modalities, such as regular photographs, infrared photography and X-Ray images. Moreover, we propose an efficient solution to improve the CNN-based localization of the actual crack boundaries and extend the CNN architecture such that areas where it makes little sense to run expensive learning models are ignored. This allows us to process large resolution scans of paintings more efficiently. The proposed on-line method is capable of continuously learning from newly acquired visual data, thus further improving classification results as more data becomes available. A case study on multimodal acquisitions of the Ghent Altarpiece, taken during the currently ongoing conservation-restoration treatment, shows improvements over the state-of-the-art in crack detection methods and demonstrates the potential of our proposed method in assisting art conservators.INDEX TERMS Digital painting analysis, crack detection, virtual restoration, machine learning, morphological filtering, convolutional neural networks, transfer learning, multimodal data, Ghent Altarpiece.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.