Landmine and Unexploded Ordnance Detection and Classification with Ground Penetrating Radar

Yarovoy, Alexander

doi:10.1016/b978-0-444-53348-7.00014-4

Cited by 20 publications

(12 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They consist in summing up intensities along A-scans within a C-scan, and thus, a surface 2-D map of potentially suspicious places is generated [1]. In [5], Bhuiyan and Nath worked with B-scans and use a seeded-growing approach for image segmentation and discovering places of interest.…”

Section: A Review Of Some Detection Approachesmentioning

confidence: 99%

“…A MONG landmine detection applications of ground penetrating radar (GPR) found in the literature, e.g., in [1]- [7], most studies are typically focused on two elements: imaging/ preprocessing techniques and features extraction techniques. One might say that these two elements are of primary importance, because, clearly, the visual quality of images and the descriptive ability of extracted features have a crucial impact on the accuracy obtained later by a given learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Analysis of C-Scans From Ground Penetrating Radar via 3-D Haar-Like Features With Application to Landmine Detection

Klęsk

Godziuk

Kapruziak

et al. 2015

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

This paper aimed to devise an efficient algorithm applicable to ground penetrating radar (GPR) and to enable an automatic landmine detection. Proposed is a machine learning approach in which we put the main emphasis on fast performance of the scanning procedure analyzing the C-scans, i.e., 3-D images defined over the coordinate system, i.e., along track by across track by time, where the time axis can be associated with depth. The approach is based on our proposition of 3-D Haar-like features. Learning of the detector is carried out by boosted decision trees.Practical experiments on metal and plastic antitank mines in a garden soil are carried out. A prototype mobile platform is designed to scan the subsurface of the ground, equipped with a GPR based on a standard vector network analyzer and our original antenna system. We report the results, particularly the following: detection sensitivity, false alarm rates, receiver operating characteristic curves, and times of learning and detection.

show abstract

Section: A Review Of Some Detection Approachesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fast Analysis of C-Scans From Ground Penetrating Radar via 3-D Haar-Like Features With Application to Landmine Detection

Klęsk

Godziuk

Kapruziak

et al. 2015

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Ground penetrating radar (GPR) is a useful technology for the detection of landmines and unexploded ordinance (UXO) [1]. Conventional GPR senses inhomogeneities in the complex permittivity of the soil.…”

Section: Introductionmentioning

confidence: 99%

Polarimetric invariants for detection by forward-looking ground penetrating radar

Chun¹,

Chun²

2011

2011 IEEE RadarCon (RADAR)

View full text Add to dashboard Cite

The usefulness of ground penetrating radar to detect landmines has been limited because of low signal-to-clutter ratios which result in high false alarm rates. We describe a method using polarimetric radar to measure the polarizability angle, the relative phase, and the target magnitude. These three independent quantities are directly related to target shape and dimensions and are invariant to rotation about the sensor-to-target axis. Data collected on an automobile disk brake rotor over a frequency range of 1.35-2.14 GHz showed that the polarizability angle and the relative phase varied less with frequency when the rotor was buried than when laying on the surface. The target magnitude showed similarities to interference patterns from scattering centers at the edges of a cylinder.

show abstract

“…The characteristics of underground objects are identified through pseudo-imaging and signal processing. GPR has become a valuable tool in several applications, such as archaeological explorations [1], glacier and ice sheet investigation [2,3], detection and monitoring of below-ground biological structures [3], mineral exploration and resource evaluation [4], building condition assessment [2], road pavement analysis [3,5], and landmine detection [6]. This paper addresses the problem of sparse representation (SR) of GPR signals.…”

Section: Introductionmentioning

confidence: 99%

Sparse Representation of GPR Traces With Application to Signal Classification

Shao

Bouzerdoum

Phung

2013

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Sparse representation (SR) models a signal with a small number of elementary waves using an overcomplete dictionary. It has been employed for a wide range of signal and image processing applications, including denoising, deblurring, and compression. In this paper, we present an adaptive SR method for modeling and classifying ground penetrating radar (GPR) signals. The proposed method decomposes each GPR trace into elementary waves using an adaptive Gabor dictionary. The sparse decomposition is used to extract salient features for SR and classification of GPR signals. Experimental results on real-world data show that the proposed sparse decomposition achieves efficient signal representation and yields discriminative features for pattern classification. © 1980-2012 IEEE.

show abstract

Landmine and Unexploded Ordnance Detection and Classification with Ground Penetrating Radar

Cited by 20 publications

References 58 publications

Fast Analysis of C-Scans From Ground Penetrating Radar via 3-D Haar-Like Features With Application to Landmine Detection

Fast Analysis of C-Scans From Ground Penetrating Radar via 3-D Haar-Like Features With Application to Landmine Detection

Polarimetric invariants for detection by forward-looking ground penetrating radar

Sparse Representation of GPR Traces With Application to Signal Classification

Contact Info

Product

Resources

About