Landmine detection with ground penetrating radar using hidden Markov models

Gader, Paul D.; Mystkowski, Miroslaw; Zhao, Yunxin

doi:10.1109/36.927446

Cited by 237 publications

(137 citation statements)

References 30 publications

Supporting

Mentioning

137

Contrasting

Order By: Relevance

“…However, the sensitivity of GPR systems to changes in local environmental conditions results in highly variable responses from buried objects that hinders correct hyperbola detection. In this scenario, detection algorithms based on statistical feature extraction from GPR images, including edge histogram descriptors [11], histograms of oriented gradients [12], hidden Markov models [13] among others, proved to have robust performance to a wide variety of data.…”

Section: Introductionmentioning

confidence: 99%

Landmine detection from GPR data using convolutional neural networks

Lameri

Lombardi

Bestagini

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-The presence of buried landmines is a serious threat in many areas around the World. Despite various techniques have been proposed in the literature to detect and recognize buried objects, automatic and easy to use systems providing accurate performance are still under research. Given the incredible results achieved by deep learning in many detection tasks, in this paper we propose a pipeline for buried landmine detection based on convolutional neural networks (CNNs) applied to groundpenetrating radar (GPR) images. The proposed algorithm is capable of recognizing whether a B-scan profile obtained from GPR acquisitions contains traces of buried mines. Validation of the presented system is carried out on real GPR acquisitions, albeit system training can be performed simply relying on synthetically generated data. Results show that it is possible to reach 95% of detection accuracy without training in real acquisition of landmine profiles.

show abstract

Section: Introductionmentioning

confidence: 99%

Landmine detection from GPR data using convolutional neural networks

Lameri

Lombardi

Bestagini

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

show abstract

“…In particular, they are frequently selected for landmine detection [2,[29][30][31][32][33]. In addition, an attempt to use a metal detector and a GPR together in the landmine detection has been made [34].…”

Section: Introductionmentioning

confidence: 99%

“…Various types of features are proposed in order to obtain features unique to a landmine. Features can be extracted in either time or frequency domain [29,32,33,38]. Once features of a landmine are available, they are compared with those in a database containing landmine features and the associated information of various landmines and burial conditions.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, a systematic decision algorithm needs to be employed. For a robust decision, methods such as hidden Markov models [32,39], Mahalanobis distance [33] and Support Vector Machine [40] are studied. Wilson et al [41] review four algorithms for landmine detection and discrimination using GPR: hidden Markov model (HMM) algorithm, geometric feature FOWA ROCA algorithm, spectral confidence feature algorithm and edge histogram discrimination algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Feature Based Detection of Landmines Using Ground Penetrating Radar

Park¹,

Park²,

Kim³

et al. 2013

PIER

View full text Add to dashboard Cite

Abstract-In this paper, we present a method for detecting antitank or anti-personnel landmines buried in the ground. A set of data generated by a ground penetrating radar is processed to remove the surface reflection and clutter, yielding signals for possible landmines. In order to detect landmines in the signals, features are computed and compared against a database, which contains those of various landmines. Three features are proposed to use; principal components from principal component analysis, Fourier coefficients and singular values from singular value decomposition method, each of which is chosen to represent each landmine uniquely. Detection is performed using Mahalanobis distance-based method. Examples show that the proposed method can effectively detect landmines in various burial condition.

show abstract

“…The probes are in the form of hollow tubes that not only measure the stiffness of the soil but also scratch the surface of the buried objects and transfer the dust to a miniature onboard mass spectrometer to determine whether the surface is a plastic, metal, wood, or other material that can be used in landmines. Remote sensing is the other methodology in which the presence of an unexpected object on or underneath the surface is examined using sensors such as electromagnetic induction sensors (EMI) [8][9][10], X ray backscatter radiography [11], ground penetrating radar (GPR) [8,10,12], infrared cameras (IR) [13], and thermal neutron analyzers. Although prodding may yield more reliable results, remote sensing is considered more appropriate for robotics applications because it is significantly faster, safer, and more attainable.…”

Section: Introductionmentioning

confidence: 99%

Landmine detection using an autonomous terrain‐scanning robot

Najjaran

Goldenberg

2005

Industrial Robot: An International Journal

View full text Add to dashboard Cite

/npsi/ctrl?lang=en http://nparc.cisti-icist.nrc-cnrc.gc.ca/npsi/ctrl?lang=fr Access and use of this website and the material on it are subject to the Terms and Conditions set forth at http://nparc.cisti-icist.nrc-cnrc.gc.ca/npsi/jsp/nparc_cp.jsp?lang=en NRC Publications Archive Archives des publications du CNRCThis publication could be one of several versions: author's original, accepted manuscript or the publisher's version. / La version de cette publication peut être l'une des suivantes : la version prépublication de l'auteur, la version acceptée du manuscrit ou la version de l'éditeur. For the publisher's version, please access the DOI link below./ Pour consulter la version de l'éditeur, utilisez le lien DOI ci-dessous.http://dx.doi.org/10.1108/01439910510593938Industrial Robot Journal, 32, 3, pp. 240-247, 2005-05-01 Landmine detection using an autonomous terrain-scanning robot Najjaran, H.; Goldenberg, A. AbstractThis paper describes the software of a terrain scanning robot capable of autonomously manipulating a typical handheld detector for remote sensing of buried landmines in a manner similar to a human operator. The autonomous manipulation of the detector on unknown terrain requires an online terrain map to generate an obstacle free path for the end effector of the robot. The software includes a twofold process of map building and path planning that is implemented into a real-time software platform to take place in parallel to the other functions of the robot.Map building features a distributed sensor fusion system to tackle the uncertainties associated with the sensor data. It provides local terrain maps by fusing the redundant measurements and complementary data obtained from competitive rangefinders and joint position sensors, respectively.The fusion takes place in a multi-step data processing module that includes a batch processing filter, a static filter, and a fuzzy adaptive Kalman filter. The latter requires the dynamic model of the process so that a stochastic model is introduced for the terrain undulations. An important parameter of the model, which significantly influences the output of the filter, is the standard deviation of the probability distribution of the process disturbances. A systematic fuzzy modeling technique is used to determine the standard deviation based on the terrain type and to adapt the filter, accordingly. The outlier rejection is carried out using the Mahalanobis distance between the estimated states of the system and the new measurements.Path planning is carried out based on the terrain map to move the detector at a constant distance and parallel to the ground. Unlike the traditional methods, the path is generated in the non-Cartesian coordinate frame of the sensors to avoid a great deal of transformations involved in reproducing the terrain map in a Cartesian coordinate frame.

show abstract

Landmine detection with ground penetrating radar using hidden Markov models

Cited by 237 publications

References 30 publications

Landmine detection from GPR data using convolutional neural networks

Landmine detection from GPR data using convolutional neural networks

Multi-Feature Based Detection of Landmines Using Ground Penetrating Radar

Landmine detection using an autonomous terrain‐scanning robot

Contact Info

Product

Resources

About