Semi-automated detection of looting in Afghanistan using multispectral imagery and principal component analysis

High-resolution satellite imagery has proved to be a powerful tool for calculating the extent of looting at heritage sites in conflict zones around the world. Monitoring damage over time, however, has been largely dependent upon laborious and error-prone manual comparisons of satellite imagery taken...

Full description

Saved in:
Bibliographic Details
Published in:Antiquity 2017-10, Vol.91 (359), p.1344-1355
Main Authors: Lauricella, Anthony, Cannon, Joshua, Branting, Scott, Hammer, Emily
Format: Article
Language:English
Subjects:
Archaeology
Automation
Cultural heritage
Digital imaging
Excavation
Historic artifacts
Imagery
Looting
Method
Preservation
Principal components analysis
Prone
Research methodology
Satellites
Time use
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:High-resolution satellite imagery has proved to be a powerful tool for calculating the extent of looting at heritage sites in conflict zones around the world. Monitoring damage over time, however, has been largely dependent upon laborious and error-prone manual comparisons of satellite imagery taken at different dates. The semi-automated detection process presented here offers a more expedient and accurate method for monitoring looting activities over time, as evidenced at the site of Ai Khanoum in Afghanistan. It is hoped that this method, which relies upon multispectral imagery and principal component analysis, may be adapted to great effect for use in other areas where heritage loss is of significant concern.
ISSN:0003-598X
1745-1744
DOI:10.15184/aqy.2017.90