Pattern recognition and automatic feature extraction in GIS.
Archaeological applications of geographic information systems and remote sensing technologies are becoming increasingly popular, especially in regard to site prospection and the geospatial analysis of cultural features. Utilizing aerial LiDAR and high-resolution satellite imagery of North Dakota, a training data set was used to define the boundaries and characteristics for certain morphological features of anthropogenic origin, which include mounds, earth lodge depressions, and fortification ditches. From this, a data mining algorithm was developed to adapt machine learning into an automated extraction program. This system was then tested on other data sets aimed at detecting similar, unrecorded features in the landscape, and verified in the field through ground truthing to determine accuracy. Implications for the successful development of this technology will allow archaeological investigators to review topography and locate specific anthropogenic features on the surface that can otherwise be difficult to distinguish in the field due to vegetation cover, terrain, or landowner permissions. Additionally, it could reduce the amount of time ground crews spend in the field and provide the researcher with site leads and an accurate model of feature distribution within a project area.
SAA 2015 abstracts made available in tDAR courtesy of the Society for American Archaeology and Center for Digital Antiquity Collaborative Program to improve digital data in archaeology. If you are the author of this presentation you may upload your paper, poster, presentation, or associated data (up to 3 files/30MB) for free. Please visit http://www.tdar.org/SAA2015 for instructions and more information.
This Resource is Part of the Following Collections
Cite this Record
Pattern recognition and automatic feature extraction in GIS.. Matthew Radermacher, Stephanie Day, Anne Denton, Jeffrey Clark, Donald Schwert. Presented at The 80th Annual Meeting of the Society for American Archaeology, San Francisco, California. 2015 ( tDAR id: 397756)
min long: -113.95; min lat: 30.751 ; max long: -97.163; max lat: 48.865 ;