The effect of translational variance in training and testing images on supervised buried threat detection algorithms for ground penetrating radar

Daniel Reichman, Leslie M. Collins, Jordan M. Malof

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A large body of recent research has focused on the development of supervised buried threat detection algorithms for ground penetrating radar (GPR) data. Such algorithms learn to automatically identify landmines in GPR data based on threat data and non-threat data examples. Training data typically consists of small 2-dimensional images that are extracted from a larger image, or volume, of GPR data. Currently, the most popular criterion for choosing training (or testing) patches is high GPR signal energy. In this work, we investigate translational variance in the patches, which occurs when relevant GPR signals (e.g., hyperbolic landmine signals) are not consistently centered, or aligned, in the extracted patches. In this work, we (i) provide evidence suggesting that translational variance is introduced into the data when popular energy based patch extraction methods are employed, and (ii) estimate the classification performance loss in supervised algorithms due to this effect. We present a simple method to help alleviate the translational variance problem. We hypothesize that reducing translational variance prior to supervised learning may facilitate the use, and success, of image features.

Original languageEnglish
Title of host publication2017 9th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2017 - Proceedings
EditorsAntonios Giannopoulos, Craig Warren
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509054848
DOIs
StatePublished - Jul 28 2017
Event9th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2017 - Edinburgh, United Kingdom
Duration: Jun 28 2017Jun 30 2017

Publication series

Name2017 9th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2017 - Proceedings

Conference

Conference9th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2017
Country/TerritoryUnited Kingdom
CityEdinburgh
Period06/28/1706/30/17

Keywords

  • ground penetrating radar
  • landmine detection
  • training

Fingerprint

Dive into the research topics of 'The effect of translational variance in training and testing images on supervised buried threat detection algorithms for ground penetrating radar'. Together they form a unique fingerprint.

Cite this