Title :
Application of Hough Forests for the detection of grave mounds in high-resolution satellite imagery
Author :
Caspari, Gino ; Balz, Timo ; Liu Gang ; Xinyuan Wang ; Mingsheng Liao
Author_Institution :
Inst. of Archaeology, Univ. of Hamburg, Hamburg, Germany
Abstract :
The conditions in the Altai Mountains make it a difficult area for archaeological on-ground surveys. Automatic surveying could facilitate decision making and planning as well as the building of a comprehensive database of archaeological monuments. We have tried three different approaches towards automatic detection of grave mounds in high-resolution optical data and found an object-class specific Hough forest algorithm the most suitable for the purpose. Through adaption and testing of the algorithm on IKONOS-2 data we created a tool for mapping archaeological features in the Altai Mountains, hence contributing to future steps towards a sustainable cultural heritage management.
Keywords :
archaeology; terrain mapping; Altai Mountains condition; Hough forest application; IKONOS-2 data; algorithm adaption; algorithm testing; archaeological feature mapping; archaeological on-ground survey; automatic grave mound detection; automatic surveying; comprehensive archaeological monument database; decision making; decision planning; grave mound detection; high-resolution optical data; high-resolution satellite imagery; object-class specific Hough forest algorithm; sustainable cultural heritage management; Computer vision; Cultural differences; Feature extraction; Iron; Satellites; Training; Vegetation;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International
Conference_Location :
Quebec City, QC
DOI :
10.1109/IGARSS.2014.6946572
