Advances in Archaeological Site Detection and Geospatial Mapping

The field of archaeological research is undergoing significant transformations with the integration of artificial intelligence and remote sensing technologies. Researchers are leveraging deep learning models and large-scale satellite imagery to identify and classify archaeological sites, as well as to reconstruct building boundaries and detect geographic objects. Notably, the use of older satellite imagery, such as CORONA, has been shown to improve the accuracy of site detection, even in areas where the landscape has been significantly altered. Furthermore, innovations in object detection and representation are enabling the creation of high-quality spatial maps, which can be used for a range of applications, including urban planning and environmental monitoring. Some noteworthy papers in this area include: The paper on AI-ming backwards, which demonstrated the efficacy of using AI techniques and CORONA imagery to discover archaeological sites that are no longer visible. The paper on HoliTracer, which introduced a novel framework for holistic vectorization of geographic objects from large-size remote sensing imagery. The paper on Transformer Based Building Boundary Reconstruction, which proposed a deep learning methodology for reconstructing building footprints from satellite imagery.

Sources

AI-ming backwards: Vanishing archaeological landscapes in Mesopotamia and automatic detection of sites on CORONA imagery

Signs of the Past, Patterns of the Present: On the Automatic Classification of Old Babylonian Cuneiform Signs

HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery

Transformer Based Building Boundary Reconstruction using Attraction Field Maps

Towards Large Scale Geostatistical Methane Monitoring with Part-based Object Detection

Built with on top of