Anomaly detection of subsurface objects using handheld ground-penetrating radar

Ho, K. C.; Harris, Samuel; Zare, Alina; Cook, Matthew

doi:10.1117/12.2178584

Cited by 5 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As discussed in Section 6.3, the algorithms in this paper are tested on a corpus of alarms generated by a prescreener developed by Ho et al 18 The prescreener outputs 3,069 alarms in total; 187 are examples of targets, and 2882 are examples of false alarms. The data was collected over 12 lanes at an eastern US test site.…”

Section: Resultsmentioning

confidence: 99%

“…The algorithms in this paper are tested on alarms generated by a prescreener developed by Ho et al 18 as the prescreener has shown good performance and yields alarms that are almost evenly spatially distributed across the lanes. This prescreener, much like any energy based prescreener, is not guaranteed to yield an alarm directly at the center of the target, so it is important to center the target before obtaining a decision statistic when analyzing a shape-based detection algorithm.…”

Section: Centering the Target In A B-scanmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging robust principal component analysis to detect buried explosive threats in handheld ground-penetrating radar data

et al. 2015

View full text Add to dashboard Cite

A goal of ground penetrating radar (GPR) preprocessing is to distinguish background from data containing explosive threats. This is commonly achieved by performing depth-dependent mean and standard deviation normalization, where the mean and standard deviation are computed on background data. Under the assumption that data with explosive threats have different statistical characteristics than the background/clutter, after normalization explosive threat data will have larger absolute normalized scores than the background/clutter. An underlying problem is determining which data to compute the background mean and standard deviation statistics over. Often the background statistics are computed over a moving window, which is centered at the location of interest and has a predetermined guard band, a region of data that is ignored. However, buried explosive threats vary considerably in their shapes and more importantly sizes subsequently, the size of the GPR responses from these objects are considerably varied. We examine a number of additional detection methods that utilize Robust Principal Component Analysis (RPCA), where RPCA decomposes the data into low-rank and sparse components. Intuitively, the low-rank component should capture the background data and the sparse should capture the anomalous explosive threat response. We find that detection performance using energy-and shape-based detection algorithms improves when using RPCA preprocessing.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Centering the Target In A B-scanmentioning

confidence: 99%

Leveraging robust principal component analysis to detect buried explosive threats in handheld ground-penetrating radar data

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Typically, this normalized value is then summed over all depths of interest. Inspired by the PCA method of prescreening [10], we sum the normalized data over different regions -shallow and deep -and then take the maximum of the shallow and deep scores. The shallow range is over depth samples 30 -150, and the deep range is from 125 -245.…”

Section: Resultsmentioning

confidence: 99%

“…We consider only the false alarms reported from a PCA based prescreener [10], which thus far has the single best prescreener performance. Due to other objects (e.g., stakes, rope) along the lane edge, all false alarms must be more than 15 samples from the beginning/end of the advance.…”

Section: Datamentioning

confidence: 99%

Buried threat detection using a handheld ground penetrating radar system

et al. 2015

View full text Add to dashboard Cite

In this work, we explore the efficacy of two buried threat detectors on handheld data. The first algorithm is an energy-based algorithm, which computes how anomalous a given A-scan measurement after it is normalized according to its local statistics. It is based on a commonly used prescreener for the Husky Mounted Detection System (HMDS). In the HMDS setting measurements are sampled on a crosstrack-downtrack grid, and sequential measurements are at neighboring downtrack locations. In contrast, in the handheld setting sequential scans are often taken at neighboring crosstrack locations, and neighboring downtrack locations can be hundreds of scans away. In order to include both downtrack and crosstrack information, we compute local statistics over a much larger area than in the HMDS setting. The second algorithm is a shape-based algorithm. Shape Invariant Feature Transform (SIFT) features, which capture the gradient distributions of local patches, are extracted and used to train a non-linear Support Vector Machine (SVM). We found that in terms of AUC, the SIFT-SVM algorithm results in a 2.2% absolute improvement over the energy-based algorithm, with the greatest gains seen at lower false alarm rates.

show abstract

“…This identity has previously been used for background estimation in anomaly detection using a ground penetrating radar system. 17 The mean and covariance estimates are updated using a lagging window running total style estimation. For the WEMI data sets used in our experiments, the first N samples can be assumed to contain mostly background points.…”

Section: Woodbury Identity Updated Acementioning

confidence: 99%

Adaptive coherence estimator (ACE) for explosive hazard detection using wideband electromagnetic induction (WEMI)

et al. 2016

Self Cite

View full text Add to dashboard Cite

The adaptive coherence estimator (ACE) estimates the squared cosine of the angle between a known target vector and a sample vector in a transformed coordinate space. The space is transformed according to an estimation of the background statistics, which directly effects the performance of the statistic as a target detector. In this paper, the ACE detection statistic is used to detect buried explosive hazards with data from a Wideband Electromagnetic Induction (WEMI) sensor. Target signatures are based on a dictionary defined using a Discrete Spectrum of Relaxation Frequencies (DSRF) model. Results are summarized as a receiver operator curve (ROC) and compared to other leading methods.

show abstract

Anomaly detection of subsurface objects using handheld ground-penetrating radar

Cited by 5 publications

References 5 publications

Leveraging robust principal component analysis to detect buried explosive threats in handheld ground-penetrating radar data

Leveraging robust principal component analysis to detect buried explosive threats in handheld ground-penetrating radar data

Buried threat detection using a handheld ground penetrating radar system

Adaptive coherence estimator (ACE) for explosive hazard detection using wideband electromagnetic induction (WEMI)

Contact Info

Product

Resources

About