Classification of aircraft using micro-Doppler bicoherence-based features

Molchanov, Pavlo; Егиазарян, Карен; Astola, Jaakko; Totsky, A. V.; Лещенко, С. П.; Jarabo-Amores, María-Pilar

doi:10.1109/taes.2014.120266

Cited by 68 publications

(27 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [10], a set of features is evaluated by using the singular value decomposition (SVD) on the spectrograms and estimating the standard deviation of the first right singular vector. In [11], Molchanov et al propose a method for the extraction of cepstrum-and bicoherence-based features from TFD for aircraft classification. In [12], the features are estimated as the Fourier series coefficients of the spectrogram envelope, whereas in [13] the mel-frequency cepstral coefficients (MFCC) are employed with the main aim to recognize human falling from other motions, which can be used for healthcare applications.…”

Section: Introductionmentioning

confidence: 99%

On Model, Algorithms, and Experiment for Micro-Doppler-Based Recognition of Ballistic Targets

Persico

Clemente

Gaglione

et al. 2017

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

The ability to discriminate between ballistic missile warheads and confusing objects is an important topic from different points of view. In particular, the high cost of the interceptors with respect to tactical missiles may lead to an ammunition problem. Moreover, since the time interval in which the defense system can intercept the missile is very short with respect to target velocities, it is fundamental to Manuscript

show abstract

Section: Introductionmentioning

confidence: 99%

On Model, Algorithms, and Experiment for Micro-Doppler-Based Recognition of Ballistic Targets

Persico

Clemente

Gaglione

et al. 2017

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

show abstract

“…Micro-Doppler based target classification applications have been employed for different target types, namely human activities (Kim and Hao, 2009), aerial targets (Molchanov et al, 2014), and ground targets (Li et al, 2011). Variant radar modes have also been used in the classification process including continuous wave radar (Kim and Hao, 2009) and SAR/GMTI (Li et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Ensemble-empirical-mode-decomposition based micro-Doppler signal separation and classification

Chen

Lin

Emrith

et al. 2017

IJCAT

View full text Add to dashboard Cite

Abstract:The target echo signals obtained by Synthetic Aperture Radar (SAR) and Ground Moving Target Indicator (GMTI) platforms are mainly composed of two parts, the microDoppler signal and the target body part signal. The wheeled vehicle and the track vehicle are classified according to the different character of their micro-Doppler signal. In order to overcome the mode mixing problem in Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD) is employed to decompose the original signal into a number of Intrinsic Mode Functions (IMF). The correlation analysis is then carried out to select IMFs which have a relatively high correlation with the micro-Doppler signal. Thereafter, four discriminative features are extracted and Support Vector Machine (SVM) classifier is applied for classification. The experimental results show that the features extracted after EEMD decomposition are effective, with up 90% success rate for classification using one feature. In addition, these four features are complementary in different target velocity and azimuth angles.Keywords: micro-Doppler; micro-motion; EEMD; IMF; wheeled/tracked vehicle; SAR/GMTI; signal separation; feature abstraction; vehicle classification; SVM Reference to this paper should be made as follows: Chen, H., Lin, P., Emrith,K., Narayan, P. and and classification, statistical learning for vision based systems, dimensionality reduction techniques, and higher-order statistics.

show abstract

“…Other researchers conducted numerical simulations and real experiments, which demonstrated that the μ-D signature represents the kinetic motions of an object and provides a viable means for object identification [3]- [5]. Micro-Doppler signals have been used for classifying rigid targets, such as helicopters and aircrafts [6], and wheel and track vehicles [7]. They have also been used to differentiate rigid and non-rigid targets, e.g.…”

Section: Introductionmentioning

confidence: 99%

Classification of micro‐Doppler signatures of human motions using log‐Gabor filters

Tivive

Phung

Bouzerdoum

2015

IET Radar, Sonar & Navigation

View full text Add to dashboard Cite

In recent years, Doppler radar has been used as a sensing modality for human gait recognition, due to its ability to operate in adverse weather and penetrate opaque obstacles. Doppler radar captures not only the speed of the target, but also the micro-motions of its moving parts. These micro-motions induce frequency modulations that can be used to characterise the target movements. However, a major challenge in Doppler signal processing is to extract discriminative features from the radar returns for target classification. This study presents a feature extraction method for classification of human motions from the micro-Doppler radar signal. The proposed method applies the log-Gabor filters at multiple spatial frequencies and orientations on a joint time-frequency representation. To achieve invariance to the target speed, features are extracted from local patches along the torso Doppler shift. Then, the (2D)2PCA (two-directional two-dimensional principal component analysis) method is applied to create a compact feature vector. Experimental results based on real radar data obtained from multiple human subjects demonstrate the effectiveness of the proposed approach in classifying arm motions.Abstract-In recent years, Doppler radar has been used as a sensing modality for human gait recognition, due to its ability to operate in adverse weather and penetrate opaque obstacles. Doppler radar captures not only the speed of the target, but also the micro-motions of its moving parts. These micro-motions induce frequency modulations that can be used to characterize the target movements. However, a major challenge in Doppler signal processing is to extract discriminative features from the radar returns for target classification. This study presents a feature extraction method for classification of human motions from the micro-Doppler radar signal. The proposed method applies the log-Gabor filters at multiple spatial frequencies and orientations on a joint time-frequency representation. To achieve invariance to the target speed, features are extracted from local patches along the torso Doppler shift. Then, the (2D) 2 PCA method is applied to create a compact feature vector. Experimental results based on real radar data obtained from multiple human subjects demonstrate the effectiveness of the proposed approach in classifying arm motions.Index Terms-Human micro-Doppler signature classification, feature extraction, S-method, Log-Gabor filters. ∞ −∞

show abstract

Classification of aircraft using micro-Doppler bicoherence-based features

Cited by 68 publications

References 22 publications

On Model, Algorithms, and Experiment for Micro-Doppler-Based Recognition of Ballistic Targets

On Model, Algorithms, and Experiment for Micro-Doppler-Based Recognition of Ballistic Targets

Ensemble-empirical-mode-decomposition based micro-Doppler signal separation and classification

Classification of micro‐Doppler signatures of human motions using log‐Gabor filters

Contact Info

Product

Resources

About