Automatic Detection and Classification of Buried Objects Using Ground‐Penetrating Radar for Counter‐Improvised Explosive Devices

Abstract

In this paper, a technique that can automatically detect and classify objects buried under the ground is proposed. The technique employs a ground‐penetrating radar that transmits electromagnetic waves in order to strike the objects and then receives the backscattering electromagnetic wave to perform signal processing. This signal processing is divided into four main steps as follows. First, preprocessing is used to reduce the clutter due to the effect of the media layer interface. Second, the late time of the scattering signal is estimated using a simple cross correlation. Third, a few successive poles are extracted from the scattering response at the estimated late time by using the short‐time matrix pencil method. Finally, the extracted poles are fed for object classification with different constitutions and/or shapes using a support vector machine. Simulations according to the practical situation in three southern provinces of Thailand to counter the improvised explosive devices were set up. The performance of the proposed technique was evaluated. The simulation results showed that the proposed technique can efficiently detect and classify buried objects for counter‐improvised explosive device operations in the military.

Robust Chipless RFID Detection Using Complex Natural Frequency Along With the k-Nearest Neighbor Algorithm

“…Second, the Euclidean distance is generalized and then referred to as the Minkowski distance, whose equation is expressed as (13).…”

“…In this approach, the principle of the singularity expansion method (SEM) was applied to encode the tag ID into the tag's structure with the CNR, generally called the pole, and to retrieve the tag ID from the late-time portion of the tag response by using the matrix pencil method (MPM). The main drawback of the MPM is that is requires prior knowledge of the commencement of the late time, which relies upon the geometry and orientation of objects [12], [13]. However, this knowledge is unknown for the non-cooperative scenario.…”

“…The STMPM was slightly modified from the MPM by sliding the time windows by step times in order to mainly distinguish the late-time portion from the whole response. The STMPM was not only applied to the chipless RFID applications, but also to the radar target identification, as we proposed in [12], [13], [15]- [17]. In [18], the design and implementation of the high-density chipless RFID tag was proposed by using the basic principle of the SEM.…”

Mapping the Physical and Dielectric Properties of Layered Soil Using Short-Time Matrix Pencil Method-Based Ground-Penetrating Radar

“…1 in which its peak is not notable. We also proposed the use of poles extracted from the GPR frequency response by using the short-time matrix pencil method (STMPM) in order to automatically detect and classify buried improvised explosive devices (IEDs) [22]. This paper proposes the use of poles to map the physical and dielectric properties of the layered soil, instead of directly using the frequency response whose Q-factor is generally low.…”

“…The solid lines that denote the separating hyperplanes being employed as decision boundaries were expressed as fn1 = -14.2308αn1 -5.7384 and fn2 = -18.8611αn2 -9.4898 GHz. The margin perpendiculars to these hyperplanes were 2/||w1|| = 0.2925 × 10 8 and 2/||w2|| = 0.1391 × 10 8 [22]. One can map the poles to soil type strongly related to the bulk density by using these decision boundaries.…”