Reliable training of convolutional neural networks for GPR-based buried threat detection using the Adam optimizer and batch normalization

Steven Jacobson, Daniël Reichman, Joel Bjornstad, Leslie M. Collins, Jordan M. Malof

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

Abstract

The ground penetrating radar (GPR) is a remote sensing technology that has been successfully used for detecting buried explosive threats. A large body of published research has focused on developing algorithms that automatically detect buried threats using data from GPR sensors. One promising class of algorithms for this purpose is convolutional neural networks (CNNs), however CNNs suffer from overfitting due to the limited and variable nature of GPR data. One solution to this problem is to use a validation dataset during training, however this excludes valuable labeled data from training. In this work we show that two modern techniques for training CNNs - Batch Normalization and the Adam Optimizer - substantially improve CNN performance and reduce overfitting when applied jointly. We also investigate and identify useful settings for several important CNN hyperparameters: l2 regularization, Dropout, and the learning rate schedule. We find that the improved CNN (a baseline CNN, plus all of our improvements) substantially outperforms two competing conventional detection algorithms.

Original languageEnglish
Title of host publicationDetection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIV
EditorsSteven S. Bishop, Jason C. Isaacs
PublisherSPIE
ISBN (Electronic)9781510626898
DOIs
StatePublished - 2019
EventDetection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIV 2019 - Baltimore, United States
Duration: Apr 15 2019Apr 17 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11012
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceDetection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIV 2019
Country/TerritoryUnited States
CityBaltimore
Period04/15/1904/17/19

Keywords

  • Ground penetrating radar
  • buried threat detection
  • cross-validation
  • model evaluation
  • supervised learning

Fingerprint

Dive into the research topics of 'Reliable training of convolutional neural networks for GPR-based buried threat detection using the Adam optimizer and batch normalization'. Together they form a unique fingerprint.

Cite this