Semi-automated detection of looting in Afghanistan using multispectral imagery and principal component analysis. (20th September 2017)

• Record Type: Journal Article
• Authors: Lauricella, Anthony; Cannon, Joshua; Branting, Scott; Hammer, Emily
• Is Part Of: Antiquity. Volume 91:Number 359(2017)
• Page Start: 1344
• Page End: 1355
• Publication Date: 2017-09-20
• Subjects: Afghanistan, -- multispectral imagery, -- satellite imagery, -- principal component analysis, -- heritage preservation, -- looting; Archaeology -- Periodicals; Antiquities -- Periodicals; 930.05
• DOI: 10.15184/aqy.2017.90
• Languages: English
• ISSNs: 0003-598X

Abstract

Abstract: Abstract : 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.