Deep Learning Network for Classifying Target of Same Shape using RCS Time Series

The main intension of this work is to find the warhead and decoy classification and identification. Classification of radar target is one of the utmost imperatives and hardest practical problems in finding out the missile. Detection of target in the pool of decoys and debris is one of the major radas technologies widely used in practice. In this study we mainly focus on the radar target recognition in different shapes like cone, cylinder and sphere based on radar cross section (RCS). RCS is a critical element of the radar signature that is used in this work to identify the target. The concept is to focus on new technique of ML for analyzing the input data and to attain a better accuracy. Machine learning has had a significant impact on the entire industry as a result of its high computational competency for target prediction with precise data analysis. We investigated various machine learning classifiers methods to categorize available radar target data. This chapter summarizes conventional and deep learning technique used for classification of radar target.

Physical Optics Radar Cross Section predictions for an anti-ship cruise missile

The capability of the first strike is crucial in the modern battlefield. An important parameter is the radar signature or Radar Cross Section (RCS) of a weapon system, such as a fighter aircraft, a warship, or a missile, affecting the range at which this weapon system would be detected as a target by an enemy radar. If the attacker is detected too late, there will be minimal time for the defender to react, possibly not sufficient to counter the threat. The RCS of a weapon system is considered generally as classified information. However, it can be measured at a suitable measurement test range, if that weapon system is available. Otherwise, it can be predicted with the help of computational electromagnetics. Concerning the second approach, the following procedure was recently proposed: construction of a three-dimensional model of a target, based on available images and any relevant data, and then computation of the target RCS, with the Physical Optics approximative method. In the present approach, this procedure is applied to an anti-ship cruise missile in order to compute its RCS. Finally, the expected detection range for various naval radars is calculated.

Foot Gesture Recognition Using High-Compression Radar Signature Image and Deep Learning

Recently, Doppler radar-based foot gesture recognition has attracted attention as a hands-free tool. Doppler radar-based recognition for various foot gestures is still very challenging. So far, no studies have yet dealt deeply with recognition of various foot gestures based on Doppler radar and a deep learning model. In this paper, we propose a method of foot gesture recognition using a new high-compression radar signature image and deep learning. By means of a deep learning AlexNet model, a new high-compression radar signature is created by extracting dominant features via Singular Value Decomposition (SVD) processing; four different foot gestures including kicking, swinging, sliding, and tapping are recognized. Instead of using an original radar signature, the proposed method improves the memory efficiency required for deep learning training by using a high-compression radar signature. Original and reconstructed radar images with high compression values of 90%, 95%, and 99% were applied for the deep learning AlexNet model. As experimental results, movements of all four different foot gestures and of a rolling baseball were recognized with an accuracy of approximately 98.64%. In the future, due to the radar’s inherent robustness to the surrounding environment, this foot gesture recognition sensor using Doppler radar and deep learning will be widely useful in future automotive and smart home industry fields.

Using KDP Cores as a Downburst Precursor Signature

Decades of research has investigated processes that contribute to downburst development, as well as identified precursor radar signatures that can accompany these events. These advancements have increased downburst predictability, but downbursts still pose a significant forecast challenge, especially in low-shear environments that produce short-lived single and multicell thunderstorms. Additional information provided by dual-polarization radar data may prove useful in anticipating downburst development. One such radar signature is the KDP core, which can indicate processes such as melting and precipitation loading that increase negative buoyancy and can result in downburst development. Therefore, KDP cores associated with 81 different downbursts across 10 states are examined to explore if this signature could provide forecasters with a reliable and useable downburst precursor signature. KDP core characteristics near the environmental melting layer, vertical gradients of KDP, and environmental conditions were quantified to identify any differences between downbursts of varying intensities. The analysis shows that 1) KDP cores near the environmental melting layer are a reliable signal that a downburst will develop, 2) while using KDP cores to anticipate an impending downburst’s intensity is challenging, larger KDP near the melting layer and larger vertical gradients of KDP are more commonly associated with strong downbursts than weak ones, 3) downbursts occurring in environments with less favorable conditions for downbursts are associated with higher magnitude KDP cores, and 4) KDP cores evolve relatively slowly (typically longer than 15 min), which makes them easily observable with the 5-min volumetric updates currently provided by operational radars.

Microphysical and Polarimetric Radar Modeling of Hydrometeor Refreezing

A unique polarimetric radar signature indicative of hydrometeor refreezing during ice pellet events has been documented in several recent studies, yet the underlying microphysical causes remain unknown. The signature is characterized by enhancements in differential reflectivity (ZDR), specific differential phase (KDP), and linear depolarization ratio (LDR), and a reduction in co-polar correlation coefficient (ρhv) within a layer of decreasing radar reflectivity factor at horizontal polarization (ZH). In previous studies, the leading hypothesis for the observed radar signature is the preferential refreezing of small drops. Here, a simplified, one-dimensional, explicit bin microphysics model is developed to simulate the refreezing of fully melted hydrometeors, and coupled with a polarimetric radar forward operator to quantify the impact of preferential refreezing on simulated radar signatures. The modeling results demonstrate that preferential refreezing is insufficient by itself to produce the observed signatures. In contrast, simulations considering an ice shell growing asymmetrically around a freezing particle (i.e., emulating a thicker ice shell on the bottom of a falling particle) produce realistic ZDR enhancements, and also closely replicate observed features in ZH, KDP, LDR, and ρhv. Simulations that assume no increase in particle wobbling with freezing produce an even greater ZDR enhancement, but this comes at the expense of reducing the LDR enhancement. It is suggested that the polarimetric refreezing signature is instead strongly related to both the distribution of the unfrozen liquid portion within a freezing particle, and the orientation of this liquid with respect to the horizontal.

Warunki powstania zjawiska downburst nad Wrocławiem w dniu 30 VI 2016

The article presents the issue of downburst over Poland. Strong downdrafts are a great danger in aviation, but can also cause damage on the surface of the Earth. On the basis of synoptic maps, aerological and radar data the analysis of synoptic and thermodynamic conditions of the atmosphere in which the phenomenon occurred was conducted. The appearance of the cold front over Lower Silesia and the occurrence of V-notch radar signature over Wroclaw may have suggested the formation of a storm and the associated downburst.

Tilted Beam Fabry–Perot Antenna with Enhanced Gain and Broadband Low Backscattering

Communication with low radar signature platforms requires antennas with low backscatter, to uphold the low observability attribute of the platforms. In this work, we present the design for a Fabry–Perot (F-P) cavity antenna with low monostatic radar cross section (RCS) and enhanced gain. In addition, peak radiation is tilted inthe elevation plane. This is achieved by incorporating phase gradient metasurface (PGM) with absorptive frequency selective surface (FSS). The periodic surface of metallic square loops with lumped resistors forms the absorptive surface, placed on top of a partially reflecting surface (PRS) with an intervening air gap. The double-sided PRS consists of uniform metallic patches etched in a periodic fashion on its upper side. The bottom surface consists of variable-sized metallic patches, to realize phase gradient. The superstrate assembly is placed at about half free space wavelength above the patch antenna resonating at 6.6 GHz. The antenna’s ground plane and PRS together construct the F-P cavity. A peak gain of 11.5 dBi is achieved at 13° tilt of the elevation plane. Wideband RCS reduction is achieved, spanning 5.6–16 GHz, for x- and y-polarizations of normally incident plane wave. The average RCS reduction is 13 dB. Simulation results with experimental verifications are presented.

Additional radar signature for waterborne object recognition

Subject and Purpose. The article is devoted to the radio recognition of moving waterborne objects (sea-going ships). The problem lies in the lack of radar signatures, which is especially true for coherent radar in continuous mode, implying that more signatures for the waterborne object recognition is highly needed. An additional signature can be gained just by means of a simple mathematical processing of target reflection signals. This is particularly important for radio recognition systems in current use because this will hardly complicate the system structure. Hence, it will not affect its cost either. Methods and Methodology. The method developed for the retrieval of an additional radar signature characteristic of waterborne objects moving across a rough sea surface is based on a simple mathematical processing of a signal reflected from the moving waterborne object and taken from the phase output of coherent radar. The method approbation is by the mathematical modeling of signals at the phase detector output in the event of three waterborne objects such that have identical scattering cross sections but different periods of the side and keel vibrations. Results. Based on the mathematical modeling results, it has been shown that each of the local scattering centers keeps the ratio of the linear speeds of side and keel vibrations approximately the same for the same object. But the employed ratio takes different values for different objects. Conclusion. Having a single standard coherent radar in continuous mode and guided by the developed methodology, one can gain an additional signature for the target recognition, which is a ratio of the linear speeds of side and keel vibrations of the target. The suggested methodology can be used for the radio recognition of waterborne objects moving across a rough sea surface.