Enhanced discrimination among UXO-like targets using extremely low-frequency magnetic fields

Chilaka, Sailaja; Faircloth, Daniel L.; Riggs, L.S.; Nelson, H. H.

doi:10.1109/tgrs.2005.859951

Cited by 20 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, results indicated that the higher frequency half of the in-phase response contains information about the wall thickness of an ordnance. In addition, Chilaka et al [18] used an electromagnetic induction system with extremely low frequencies to improve discrimination by a factor of 1.5. The expanded frequency range enabled discrimination between thin and thickwalled ferrous cylinders, which were indistinguishable in the typical electromagnetic induction band.…”

Section: Finite Element Forward Modelingmentioning

confidence: 99%

Learning Machine Identification of Ferromagnetic UXO Using Magnetometry

Bray

Link

2015

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The fundamental problem in applying geophysical mapping to locate unexploded ordnance (UXO) is distinguishing true UXO from non-UXO. Enhancing the accuracy of UXO detection has multiple benefits, especially in the areas of cost savings and safety. We investigated discrimination approaches using both magnetic field data and numerically modeled data. Libraries of total field magnetic (TFM) responses were calculated using finite element modeling for three UXO types found at a Montana National Guard training site. UXO model parameters were varied over ranges of azimuth, declination, and depth resulting in approximately 600 models per UXO type. The modeled responses of finite-element model (FEM) and actual TFM field data were then used as training data in discrimination and classification approaches comparing neural networks (NN), random forests (RF), and support vector machines (SVMs). The prediction targets in the training process comprised three classes: 1) binary [UXO or noninteresting object (NIO)]; 2) multiclass (UXO round type and NIO); and 3) classes derived from multiclass self-organizing feature map (SOFM) analysis. The multiclass SOFM targets generated from site-specific field data were found to be optimal for UXO discrimination. The best performing combination of class selection types using recentered data for UXO detection rates of 100% resulted in a false alarm rate (FAR) of 28%. Index Terms-Classification, finite-element model (FEM), magnetics, neural networks (NN), random forest (RF), support vector machine (SVM), unexploded ordnance (UXO).

show abstract

Section: Finite Element Forward Modelingmentioning

confidence: 99%

Learning Machine Identification of Ferromagnetic UXO Using Magnetometry

Bray

Link

2015

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…n r R G r r (7) and the Since many if not all UXO are bodies of revolution (BOR), it is desirable to simplify equation (6) for BOR objects. After dividing the fictitious spheroid surface into J belts (as in Fig.…”

Section: Generalized Standardized Excitation Approach For Emi Sensorsmentioning

confidence: 99%

The generalized SEA and a statistical signal processing approach applied to UXO discrimination

et al. 2008

View full text Add to dashboard Cite

The prohibitive costs of excavating all geophysical anomalies are well known and are one of the greatest impediments to efficient clean-up of unexploded ordnance (UXO)-contaminated lands at Department of Defense (DoD) and Department of Energy (DOE) sites. Innovative discrimination techniques that can reliably distinguish between hazardous UXO and non-hazardous metallic items are required. The key element to overcoming these difficulties lies in the development of advanced processing techniques that can treat complex data sets to maximize the probability of accurate classification and minimize the false alarm rate. To address these issues, this paper uses a new approach that combines a physically complete EMI forward model called the Generalized Standardized Excitation Approach (GSEA) with a statistical signal processing approach named Mixed Modeling (MM). UXO discrimination requires the inversion of digital geophysical data, which could be divided into two pars: 1) linear -estimating model parameters such as the amplitudes of the responding GSEA sources and 2) non-linear -inverting an object's location and orientation. Usually the data inversion is an ill-posed problem that requires regularization. Determining the regularization parameter is not straightforward, and in many cases depends on personal experience. To overcome this issue, in this paper we employ the statistical approach to estimate regularization parameters from actual data using the un-surprised mixed model approach. In addition, once the non-linear inverse scattering parameters are estimated then for UXO discrimination a covariance matrix and confidence interval are derived. The theoretical basis and practical realization of the combined GSEA-Mixed Model algorithm are demonstrated. Discrimination studies are done for ATC-UXO sets of time-domain EMI data collected at the ERDC UXO test stand site in Vicksburg, Mississippi.

show abstract

“…The clearance of these UXOs has been a dangerous and expensive process [2]. About 95% of the suspected anomalies are harmless clutters, and the discrimination between buried UXOs and harmless clutters continues to be a challenge [3,4].…”

Section: Introductionmentioning

confidence: 99%

Classification of unexploded ordnance-like targets with characteristic response in transient electromagnetic sensing

et al. 2019

View full text Add to dashboard Cite

Characteristic response parameterized in time-dependent target intrinsic polarizabilities can be used to discriminate unexploded ordnance (UXO) from harmless items. This study explains the measurement, analysis, and classification of UXO-like targets against data collected under laboratory-type conditions with a specially designed transient electromagnetic (TEM) system. After a brief description of the single dipole model and TEM system, the characteristic responses of all UXO-like targets have been measured with an improved long straight solenoid. The influence of the target shape and size on characteristic response is analyzed. Results show that targets of the same shape share similar power law function decay rate at an early time. The larger the target size is, the greater the response will be. The characteristic response for harmless targets decays faster than the UXOs, leading to a considerable difference in a later time, which can be used for target classification. When the characteristic response is parameterized as kt −β e −γ t in 100 ms, targets can be effectively separated with the fitted parameters k, β and γ. However, when fitted in 10 ms, the fitted parameter γ may be thousands of times than the one fitted in 100 ms, resulting in classification failure. The normalized response combined with the fitting parameter β can be used for target classification to overcome the instability of fitted parameter γ in 10 ms. Finally, all UXOs are completely separated from harmless targets within 10 ms. K: Data processing methods; Detection of explosives; Pattern recognition, cluster finding, calibration and fitting methods 1Corresponding author.

show abstract

Enhanced discrimination among UXO-like targets using extremely low-frequency magnetic fields

Cited by 20 publications

References 28 publications

Learning Machine Identification of Ferromagnetic UXO Using Magnetometry

Learning Machine Identification of Ferromagnetic UXO Using Magnetometry

The generalized SEA and a statistical signal processing approach applied to UXO discrimination

Classification of unexploded ordnance-like targets with characteristic response in transient electromagnetic sensing

Contact Info

Product

Resources

About