English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The screening of baggage using X-ray scanners is now routine in aviationsecurity with automatic threat detection approaches, based on 3D X-ray computedtomography (CT) images, known as Automatic Threat Recognition (ATR) within theaviation security industry. These current strategies use pre-defined threatmaterial signatures in contrast to adaptability towards new and emerging threatsignatures. To address this issue, the concept of adaptive automatic threatrecognition (AATR) was proposed in previous work. In this paper, we present asolution to AATR based on such X-ray CT baggage scan imagery. This aims toaddress the issues of rapidly evolving threat signatures within the screeningrequirements. Ideally, the detection algorithms deployed within the securityscanners should be readily adaptable to different situations with varyingrequirements of threat characteristics (e.g., threat material, physicalproperties of objects). We tackle this issue using a novel adaptive machinelearning methodology with our solution consisting of a multi-scale 3D CT imagesegmentation algorithm, a multi-class support vector machine (SVM) classifierfor object material recognition and a strategy to enable the adaptability ofour approach. Experiments are conducted on both open and sequestered 3D CTbaggage image datasets specifically collected for the AATR study. Our proposedapproach performs well on both recognition and adaptation. Overall our approachcan achieve the probability of detection around 90% with a probability of falsealarm below 20%. Our AATR shows the capabilities of adapting to varying typesof materials, even the unknown materials which are not available in thetraining data, adapting to varying required probability of detection andadapting to varying scales of the threat object.

An Approach for Adaptive Automatic Threat Recognition Within 3D Computed Tomography Images for Baggage Security Screening