Investigation of Time–Frequency Features for GPR Landmine Discrimination

Savelyev, T.G.; Kempen, Luc Van; Sahli, Hichem; Sachs, J.; Suzuki, Motoyuki

doi:10.1109/tgrs.2006.885077

Cited by 82 publications

(52 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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%

“…They also note that fusion of more than two different algorithms could enhance the performance. In relation to this comment, use of multiple features for landmine detection is addressed in [33,42].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Feature Based Detection of Landmines Using Ground Penetrating Radar

Park¹,

Park²,

Kim³

et al. 2013

PIER

View full text Add to dashboard Cite

show abstract

“…A well-known application of IRT is on the detection of buried plastic antipersonnel mines, which are virtually undetectable by traditional methods, such as metal detectors. Other techniques, such as Ground Penetrating Radar (GPR), [1] have been investigated, but they fail to detect shallowly buried objects due to the large reflections coming from the soil-air interface. Given that unlike other types of mines, plastic antipersonnel mines are usually either laid on the surface or buried within a maximum depth of 10-15cm, special attention has been paid in recent years to the use of IRT for mine detection, [2].…”

Section: Introductionmentioning

confidence: 99%

GPU-based infrared thermography for NDE of minefields

Pardo¹,

López²,

Cabello³

2012

Proceedings of the 2012 International Conference on Quantitative InfraRed Thermography

View full text Add to dashboard Cite

Infrared thermography is an attractive technique for non-destructive evaluation processes and particularly for detecting shallowly buried mines. Its use consists of subjecting the area under inspection to a source of natural or artificial heating/cooling process and studying the soil's response by means of the analysis of its thermal evolution given by a temporal sequence of infrared images. To this aim an efficient solution of the heat equation is required. Over the years, different software solutions have been proposed, taking advantage of today's impressive computing power of parallel machines. In this work, we consider a hybrid software-hardware approach making use of a Graphics Processing Unit (GPU) acting as a heat equation solver with the goal of obtaining a portable system to be used during field experiments. The system has been successfully used for the non-destructive inspection of soils in mine detection applications based on infrared thermography techniques.

show abstract

FPGA computation of the 3D heat equation

et al. 2009

View full text Add to dashboard Cite

Efficient solution of the heat equation is one of the recursive topics in computational physics. Over the years, different software solutions have been proposed, taking advantage of today's impressive computing power of parallel machines. In this work, we consider a hybrid software-hardware approach making use of a field-programmable gate array platform as a heat equation solver that can be easily attached to a PC using a PCI bus with the goal of obtaining a portable system to be used during field experiments. The system has been successfully used for the non-destructive inspection of soils in mine detection applications based on infrared thermography techniques.

show abstract

Investigation of Time–Frequency Features for GPR Landmine Discrimination

Cited by 82 publications

References 21 publications

Multi-Feature Based Detection of Landmines Using Ground Penetrating Radar

Multi-Feature Based Detection of Landmines Using Ground Penetrating Radar

GPU-based infrared thermography for NDE of minefields

FPGA computation of the 3D heat equation

Contact Info

Product

Resources

About