Spectrum estimation by neural networks and their use for target classification by radar

Melendez, G.J.; Kesler, S.

doi:10.1109/icassp.1995.479769

Cited by 9 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[6][7][8][9][10]. However, these methods are mainly concentrated on estimating the interval of adjacent spectrum lines, and they often require a higher pulse repetition frequency (PRF) and longer observation time.…”

Section: Introductionmentioning

confidence: 99%

Research on Analysis of Multifractal Correlation Characteristics of Aircraft Echoes and Classification of Targets in Surveillance Radars

Li¹,

Xie²

2013

PIER B

View full text Add to dashboard Cite

Abstract-Multifractal correlation, which studies the spatial correlation characteristics of two points with different singularity indexes, is a generalization of multifractal single point statistic. This paper introduces multifractal correlation theory into the characteristic analysis of aircraft echoes from low-resolution surveillance radars, and discusses the application of multifractal correlation characteristics in target classification. Firstly, on basis of introducing multifractal correlation theory, the multifractal correlation characteristics of aircraft echoes from surveillance radars are analyzed in detail by means of the multifractal correlation analysis. Secondly, on basis of the foregoing analysis, several characteristic parameters of the echo multifractal correlation spectrum are defined, and the support vector machine (SVM) based on the defined characteristic parameters is taken as the classifier to classify different types of aircraft targets. Finally, real recorded aircraft echo data are adopted to do the classification experiments, and the experimental results validate the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on Analysis of Multifractal Correlation Characteristics of Aircraft Echoes and Classification of Targets in Surveillance Radars

Li¹,

Xie²

2013

PIER B

View full text Add to dashboard Cite

show abstract

“…The above properties are invariant to the radar line of sight angle, i.e, they agree with any radar azimuth as long as there is no shielding of the rotating structures. Most current methods of extracting JEM features are first compensating for the fuselage component signal, and then estimating the modulated wave's periodicity and the modulated Doppler line spectra's interval by parametric methods, such as complex cepstrum method [10], auto correlation method [11], periodogram method [12], AR model power spectrum method [13]. Ref.…”

Section: Introductionmentioning

confidence: 99%

Target classification with low-resolution radar based on dispersion situations of eigenvalue spectra

Chen

Liu

et al. 2010

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Most low-resolution radar systems, especially ground surveillance radar systems, work at relatively low pulse repeat frequency (PRF) and with short time-on-target (TOT) (duration in scanning). Low PRF leads to Doppler ambiguity and short TOT results in low Doppler resolution, which poses a problem to target classification with low-resolution radar based on the jet engine modulation (JEM) characteristic of radar echo. From the pattern classification viewpoint, we propose a method of using dispersion situations of JEM eigenvalue spectra to categorize aeroplanes into three kinds, namely turbojet aircraft, prop aircraft and helicopter. We analyze the mathematical model of JEM echoes consisting of a series of line spectra and regard them as a sum of several series of harmonious waves. Classification features can be extracted based on the harmonious wave sum model. Some schemes for extracting features from echoes within or between pulses are proposed. Low-dimensional features are extracted to reduce computation burden. Our methods do not compensate for the fuselage echoes and are insensitive to the variation of fuselage Doppler. The feasibility of our methods is demonstrated by simulation experiment.

show abstract

“…On basis of analyzing the performance of methods using some typical low-resolution radar target classification features [15,[24][25][26][27][28][29][30][31][32][33][34], [16] indicates that the classification method based on dispersion situations of eigenvalue spectra (CMDSES) outgoes other methods remarkably.…”

Section: Fuzzy-fractal-feature-based Classification Experimentsmentioning

confidence: 99%

Classification of Aircraft Targets With Surveillance Radars Based on Fuzzy Fractal Features

Li¹,

Xie²

2013

PIER M

View full text Add to dashboard Cite

Abstract-The fuzzy fractal characteristics of return signals from aircraft targets in conventional radars offer a description of dynamic features which induce the echo structure of targets, therefore they can provide a new way for aircraft target classification and recognition with low-resolution surveillance radars. On basis of introducing fuzzy fractal theory, the paper analyzes the fuzzy fractal characteristics of return signals from aircraft targets in a VHF-band surveillance radar by means of the fuzzy fractal analysis, and puts forward a fuzzyfractal-feature-based classification method for aircraft targets with a low-resolution radar from the viewpoint of pattern recognition. The analysis shows that the fuzzy fractal characteristic parameters such as the local fuzzy fractal dimension (LFFD) and local degree of fractality (LGF) can be used as effective features for aircraft target classification and recognition. The results of classification experiments validate the proposed method.

show abstract

Spectrum estimation by neural networks and their use for target classification by radar

Cited by 9 publications

References 3 publications

Research on Analysis of Multifractal Correlation Characteristics of Aircraft Echoes and Classification of Targets in Surveillance Radars

Research on Analysis of Multifractal Correlation Characteristics of Aircraft Echoes and Classification of Targets in Surveillance Radars

Target classification with low-resolution radar based on dispersion situations of eigenvalue spectra

Classification of Aircraft Targets With Surveillance Radars Based on Fuzzy Fractal Features

Contact Info

Product

Resources

About