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

fYear

2014

fDate

13-18 July 2014

Firstpage

906

Lastpage

909

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;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International

Conference_Location

Quebec City, QC

Type

conf

DOI

10.1109/IGARSS.2014.6946572

Filename

6946572