&lt;title&gt;Vehicle and personnel detection using seismic sensors&lt;/title&gt;

Gramann, Richard A.; Bennett, Mary Beth; O’Brien, Thomas D.

doi:10.1117/12.336952

Cited by 20 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for an in-depth description of the system hardware, see Ref. 1. The primary components of the detection and classification system, shown in Figure 1, include a single 3-axis seismic sensor, signal conditioner and preamp, and data acquisition and processing computer.…”

Section: System Hardwarementioning

confidence: 99%

“…develop a system capable of processing data from a single 3-axis seismic sensor and performing near real-time detection and feature classifications on ground vehicles in the vicinity of the sensor [1]. The detection and classification software classified a variety of vehicle features, including the number of cylinders in the engine, number of axles, engine type, traction mechanism, and relative weight.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection and classification of time-critical targets using seismic sensors

Mayoral

McCool

Gramann

2002

Unattended Ground Sensor Technologies and Applications IV

Self Cite

View full text Add to dashboard Cite

In the late 1990s, ARL:UT developed a real-time system capable of detecting and classifying a variety of vehicles using a single 3-axis seismic sensor. At that time, the detection and classification software was designed to classify vehicles for a variety of features, including the number of cylinders in the engine, number of axles, engine type, traction mechanism, and relative weight. Using a single 3-axis seismic sensor, buried approximately 3 feet deep, the demonstration system showed that it was possible to detect and classify a single time-critical target, moving with constant bearing and speed. Since then, modifications have been made to the detection and classification software in support of a transition of the algorithms into unattended MASINT sensors (UMS). This paper describes the next evolution of the detection and classification system, which focuses on generating highly accurate traction mechanism and relative weight classifications. The current build of the software has proven capable of detecting vehicles and generating high confidence classifications for a wide range of vehicles and test scenarios, and performs well for both buried and hand-emplaced sensors. Included in the paper is a description of the upgrades made to the classification algorithms, event switching, and graphical user interface (GUI), an outline of the processing and analysis of seismic data, and a summary of the software performance for a wider range of vehicles, test scenarios, and sensor configurations.

show abstract

Section: System Hardwarementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Detection and classification of time-critical targets using seismic sensors

Mayoral

McCool

Gramann

2002

Unattended Ground Sensor Technologies and Applications IV

Self Cite

View full text Add to dashboard Cite

show abstract

“…Current feature extraction methods for seismic signals can be classified into three categories, namely, time domain [8,9], frequency domain [4,10,11] and time-frequency domain [3]. On the one hand, time-domain analysis may not be able to recognize targets very accurately because of the interference noise, complicated signal waveforms and variations of the terrain [3].…”

Section: Introductionmentioning

confidence: 99%

Seismic Target Classification Using a Wavelet Packet Manifold in Unattended Ground Sensors Systems

Huang

Zhou

Zhang

et al. 2013

Sensors

View full text Add to dashboard Cite

One of the most challenging problems in target classification is the extraction of a robust feature, which can effectively represent a specific type of targets. The use of seismic signals in unattended ground sensor (UGS) systems makes this problem more complicated, because the seismic target signal is non-stationary, geology-dependent and with high-dimensional feature space. This paper proposes a new feature extraction algorithm, called wavelet packet manifold (WPM), by addressing the neighborhood preserving embedding (NPE) algorithm of manifold learning on the wavelet packet node energy (WPNE) of seismic signals. By combining non-stationary information and low-dimensional manifold information, WPM provides a more robust representation for seismic target classification. By using a K nearest neighbors classifier on the WPM signature, the algorithm of wavelet packet manifold classification (WPMC) is proposed. Experimental results show that the proposed WPMC can not only reduce feature dimensionality, but also improve the classification accuracy up to 95.03%. Moreover, compared with state-of-the-art methods, WPMC is more suitable for UGS in terms of recognition ratio and computational complexity.

show abstract

“…Nevertheless discriminating human footstep signals from other target types and noise sources is a challenging problem, because of the rapidly decreasing trend of signal to noise ratio (SNR) as the distance between the sensor and the moving target increases. Furthermore, the footstep signals have dissimilar signatures for different environments and persons, which make the problem of target detection and classification even more challenging [15]. In contrast to the Cepstrum-based and PCA-based feature extraction, the advantage of the SDF-based algorithm is that it takes into account the local information of the signal and it is capable of mitigating noise in the data even if the signal is not pre-processed for denoising.…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison of Feature Extraction Algorithms for Target Detection and Classification

Bahrampour¹,

Ray²,

Sarka³

et al. 2013

View full text Add to dashboard Cite

Abstract-This paper addresses the problem of target detection and classification, where the performance is often limited due to high rates of false alarm and classification error, possibly because of inadequacies in the underlying algorithms of feature extraction from sensory data and subsequent pattern classification. In this paper, a recently reported feature extraction algorithm, symbolic dynamic filtering (SDF), is investigated for target detection and classification by using unmanned ground sensors (UGS). In SDF, sensor time series data are first symbolized to construct probabilistic finite state automata (PFSA) that, in turn, generate low-dimensional feature vectors. In this paper, the performance of SDF is compared with that of two commonly used feature extractors, namely Cepstrum and principal component analysis (PCA), for target detection and classification. Three different pattern classifiers have been employed to compare the performance of the three feature extractors for target detection and human/animal classification by UGS systems based on two sets of field data that consist of passive infrared (PIR) and seismic sensors. The results show consistently superior performance of SDF-based feature extraction over Cepstrum-based and PCAbased feature extraction in terms of successful detection, false alarm, and misclassification rates.

show abstract

<title>Vehicle and personnel detection using seismic sensors</title>

Cited by 20 publications

References 0 publications

Detection and classification of time-critical targets using seismic sensors

Detection and classification of time-critical targets using seismic sensors

Seismic Target Classification Using a Wavelet Packet Manifold in Unattended Ground Sensors Systems

Performance Comparison of Feature Extraction Algorithms for Target Detection and Classification

Contact Info

Product

Resources

About