Sparse Time-Frequency Representation Based Feature Extraction Method for Landmine Discrimination

Wang, Yuming; Song, Qian; Tian, Jin; Shi, Yong; Huang, Xiaotao

doi:10.2528/pier12082104

Cited by 8 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Micro-Doppler is regarded as a unique signature of an object with movements where the uniqueness means different micro-motions have dissimilar signatures. Micro-Doppler signatures might be extracted for radar target identification which is seen as a good method and a technique of great potential [6,7,[9][10][11][12][13][14][15][16][17]. Since the m-D phenomenon is presented and researched by Chen et al, the extractions of the m-D signatures have developed rapidly [8,[18][19][20][21][22].…”

Section: Introductionmentioning

confidence: 99%

Features Extraction of Rotationally Symmetric Ballistic Targets Based on Micro-Doppler

Pan¹,

Wang²,

Liu³

et al. 2013

PIER

View full text Add to dashboard Cite

Abstract-It is potentially useful to perform target identification using micro-Doppler features because they contain information on the geometrical structure of the target. In this paper, the m-D effect of the rotationally symmetric ballistic target (BT) is analyzed which reveals that the m-D is not a form of sinusoidal modulation due to the slidingtype scattering. Inspired by the extended Hough transform (EHT), a method to extract all the six parameters of the BT is proposed. The m-D effect and the performance of feature extraction algorithm are demonstrated by the measured data in a microwave anechoic chamber.

show abstract

Section: Introductionmentioning

confidence: 99%

Features Extraction of Rotationally Symmetric Ballistic Targets Based on Micro-Doppler

Pan¹,

Wang²,

Liu³

et al. 2013

PIER

View full text Add to dashboard Cite

show abstract

“…Landmine detection is a tough problem of weak and small targets detection in strong clutter environment [24][25][26]. As a typical BOR target, landmine will be enhanced by ASEBOREI.…”

Section: Applications In Landmine Detectionmentioning

confidence: 99%

Body-of-Revolution-Enhanced Imaging in Ultra-Wideband Sar

Liang¹,

Song²,

Zhang³

et al. 2013

PIER

Self Cite

View full text Add to dashboard Cite

Abstract-For ultra-wideband synthetic aperture radar (UWB SAR), there often exist a lot of clutters in the image, and the weak targets are easy to be masked by them. However, using the prior scattering knowledge of targets, enhanced imaging can be realized and beneficial improvements in image quality and detection performance can be expected. In this paper, an enhanced imaging method for body of revolution (BOR) has been researched. Since the BOR target has the unique feature of aspect-invariant characteristic, the aspect scattering entropy (ASE) is proposed to describe the diversity of aspect scattering and used in the BOR-enhanced imaging method. Then the application of the proposed method in landmine detection is discussed. The experimental results show that the BOR targets are effectively enhanced and the clutters are surpressed and thus the probability of landmine detection increases under the same false alarm rate.

show abstract

“…Radar has been successfully employed for detection of various entities such as breast cancers [7][8][9], hidden objects or humans [10][11][12][13][14][15][16][17][18][19], moving targets [20][21][22] and their speed [23,24] and speech acquisition [25]. Among various types of radars developed so far, ground penetrating radars (GPRs) have attracted many researchers attention.…”

Section: Introductionmentioning

confidence: 99%

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

Sparse Time-Frequency Representation Based Feature Extraction Method for Landmine Discrimination

Cited by 8 publications

References 30 publications

Features Extraction of Rotationally Symmetric Ballistic Targets Based on Micro-Doppler

Features Extraction of Rotationally Symmetric Ballistic Targets Based on Micro-Doppler

Body-of-Revolution-Enhanced Imaging in Ultra-Wideband Sar

Multi-Feature Based Detection of Landmines Using Ground Penetrating Radar

Contact Info

Product

Resources

About