Model-based sparse recovery method for automatic classification of helicopters

Abstract

The rotation of rotor blades of a helicopter induces a Doppler modulation around the main Doppler shift. Such a non-stationary modulation, commonly called micro-Doppler signature, can be used to perform classification of the target. In this paper a model-based automatic helicopter classification algorithm is presented. A sparse signal model for radar return from a helicopter is developed and by means of the theory of sparse signal recovery, the characteristic parameters of the target are extracted and used for the classification. This approach does not require any learning process of a training set or adaptive processing of the received signal. Moreover, it is robust with respect to the initial position of the blades and the angle that the LOS forms with the perpendicular to the plane on which the blades lie. The proposed approach is tested on simulated and real data

Student research highlights: MACHe — Model-based algorithm for classification of helicopters

“…The helicopter classification method presented in [8] is an iterative automatic algorithm that is independent of both the initial position of the blades and the aspect angle (i.e. the angle between the line-of-sight and the perpendicular to the plane in which the blades lie).…”

Sparsity-based dynamic hand gesture recognition using micro-Doppler signatures

“…A pruned OMP algorithm is developed in [13], which achieves the joint estimation of the spatial distribution of the scatterers on the target and the rotational speed of the target. In [14], sparse signal processing technique is combined with the time-frequency analysis to obtain high accuracy of helicopter classification. The methods proposed in [12][13][14] are based on the analytic expressions of the micro-Doppler signals and cannot be used for dynamic hand gesture analysis, because it is difficult to analytically formulate the radar echoes of dynamic hand gestures.…”

Sparsity-Driven Micro-Doppler Feature Extraction for Dynamic Hand Gesture Recognition

“…The sparse signal processing technique [23] provides a new perspective for radar data reduction without 41 compromising performance, and this technique has been used to extract micro-Doppler features of vibrating or rotating 42 targets [24][25][26][27]. In [24], the micro-Doppler signatures induced by rotating scatterers in radar imaging applications are 43 > REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < 3 extracted by the orthogonal matching pursuit (OMP) algorithm.…”

“…A pruned OMP algorithm is developed in [25], which 44 achieves the joint estimation of the spatial distribution of the scatterers on the target and the rotational speed of the 45 target. In [26][27], the sparse signal processing technique is combined with the time-frequency analysis to obtain high 46 accuracy of helicopter classification. The methods proposed in [24][25][26][27] are based on the analytic expressions of the 47 micro-Doppler signals and cannot be used for dynamic hand gesture analysis, because it is difficult to analytically 48 formulate the radar echoes of dynamic hand gestures.…”

“…In [26][27], the sparse signal processing technique is combined with the time-frequency analysis to obtain high 46 accuracy of helicopter classification. The methods proposed in [24][25][26][27] are based on the analytic expressions of the 47 micro-Doppler signals and cannot be used for dynamic hand gesture analysis, because it is difficult to analytically 48 formulate the radar echoes of dynamic hand gestures. To the best of our knowledge, the combination of sparse signal 49 representation and the micro-Doppler analysis for dynamic hand gesture recognition has not been sufficiently 50 investigated yet.…”