• Home
  • Search
  • Dictionary Learning for Adaptive GPR Landmine Classification
  • Open Access IconOpen Access
  • Cite Icon45
  • https://doi.org/10.1109/tgrs.2019.2931134Copy DOI Icon

Dictionary Learning for Adaptive GPR Landmine Classification

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Ground penetrating radar (GPR) target detection and classification is a challenging task. Here, we consider online dictionary learning (DL) methods to obtain sparse representations (SR) of the GPR data to enhance feature extraction for target classification via support vector machines. Online methods are preferred because traditional batch DL like K-SVD is not scalable to high-dimensional training sets and infeasible for real-time operation. We also develop Drop-Off MINi-batch Online Dictionary Learning (DOMINODL) which exploits the fact that a lot of the training data may be correlated. The DOMINODL algorithm iteratively considers elements of the training set in small batches and drops off samples which become less relevant. For the case of abandoned anti-personnel landmines classification, we compare the performance of K-SVD with three online algorithms: classical Online Dictionary Learning, its correlation-based variant, and DOMINODL. Our experiments with real data from L-band GPR show that online DL methods reduce learning time by 36-93% and increase mine detection by 4-28% over K-SVD. Our DOMINODL is the fastest and retains similar classification performance as the other two online DL approaches. We use a Kolmogorov-Smirnoff test distance and the Dvoretzky-Kiefer-Wolfowitz inequality for the selection of DL input parameters leading to enhanced classification results. To further compare with state-of-the-art classification approaches, we evaluate a convolutional neural network (CNN) classifier which performs worse than the proposed approach. Moreover, when the acquired samples are randomly reduced by 25%, 50% and 75%, sparse decomposition based classification with DL remains robust while the CNN accuracy is drastically compromised.

Similar Papers
  • Research Article
  • Citations6

DUK-SVD: dynamic dictionary updating for sparse representation of a long-time remote sensing image sequence

  • Mar 29, 2017
  • Soft Computing
  • Lizhe Wang +3
  • Research Article
  • Citations8

On the fly image denoising using patch ordering

  • Nov 13, 2021
  • Expert Systems with Applications
  • Ozden Colak +1
  • Conference Article
  • Citations3

Spectral-spatial online dictionary learning for hyperspectral image classification

  • Jul 01, 2017
  • Wei Fu +3
  • Conference Article

Sparse representation for remote sensing images of long time sequences

  • Jul 01, 2014
  • Jing Wen +3
  • Conference Article
  • Citations7

Discriminative dictionary learning to learn effective features for detecting buried threats in ground penetrating radar data

  • May 03, 2017
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Jordan M Malof +2
  • Research Article
  • Citations22

SVMs multi-class loss feedback based discriminative dictionary learning for image classification

  • Oct 08, 2020
  • Pattern Recognition
  • Bao-Qing Yang +5
  • Conference Article
  • Citations1

Compressed sensing MRI using double sparsity with additional training images

  • Mar 01, 2017
  • Chenmin Tang +3
  • Conference Article
  • Citations7

Online dictionary learning aided target recognition in cognitive GPR

  • Jul 01, 2017
  • Fabio Giovanneschi +4
  • Book Chapter
  • Citations2

Deep Dictionary Pair Learning for SAR Image Classification

  • Jan 01, 2022
  • Kang Wei +5
  • Research Article
  • Citations10

Efficient and robust discriminant dictionary pair learning for pattern classification

  • Sep 06, 2021
  • Digital Signal Processing
  • Yuxi Wang +3
  • Research Article

Compact dictionary pair learning and refining based on principal components analysis

  • Sep 01, 2019
  • International Journal of Wavelets, Multiresolution and Information Processing
  • Yibin Yu +3
  • PDF
  • Research Article
  • Citations2

Compressing Sensing Based Source Localization for Controlled Acoustic Signals Using Distributed Microphone Arrays

  • Jan 01, 2017
  • Mathematical Problems in Engineering
  • Wei Ke +3
  • Research Article
  • Citations8

A novel method for GPR imaging based on neural networks and dictionary learning

  • Feb 03, 2021
  • Waves in Random and Complex Media
  • Shayan Hajipour +2
  • Conference Article
  • Citations5

Group-wise sparse representation of resting-state fMRI data for better understanding of schizophrenia

  • Apr 01, 2017
  • Lin Yuan +2
  • Research Article
  • Citations1

OCDL-ACDF: a complex-valued image denoising method based on an adaptive complex domain dictionary

  • Apr 28, 2021
  • Journal of Electronic Imaging
  • Boyu Liu +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.