No abstract

Personnel recognition and gait classification based on multistatic micro-doppler signatures using deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, (doi:10.1109/LGRS.2018.2806940) This is the author's final accepted version.There may be differences between this version and the published version. You are advised to consult the publisher's version if you wish to cite from it.http://eprints.gla.ac.uk/156827/ Abstract-In this letter we propose two methods for personnel recognition and gait classification using deep convolutional neural networks (DCNNs) based on multistatic radar micro-Doppler signatures. Previous DCNN based schemes have mainly focused on monostatic scenarios, whereas directional diversity offered by multistatic radar is exploited in our work to improve classification accuracy. We first propose the voted monostatic DCNN method (VMo-DCNN), which trains DCNNs on each receiver node separately, and fuses the results by binary voting. By merging the fusion step into the network architecture, we further propose the multistatic DCNN method (Mul-DCNN), which performs slightly better than VMo-DCNN. These methods are validated on real data measured with a 2.4 GHz multistatic radar system. Experimental results show that Mul-DCNN achieves over 99% accuracy in armed/unarmed gait classification using only 20% training data and similar performance in two-class personnel recognition using 50% training data, which are higher than the accuracy obtained by performing DCNN on a single radar node.

In a conventional synthetic aperture radar (SAR) image, a moving target may be smeared and displaced. Taking direct action on the defocused region of interest (ROI) data from the result of a conventional imaging algorithm, this paper presents an imaging method of the ground moving target in high-resolution SAR. A 2-D equivalent velocity parameter space is built along the azimuth and range directions with the derivation of an exact analytic expression of the ROI. In each pair of equivalent velocity parameters, the Stolt interpolation is used herein to remove the residual phase error. After that, a graph of the ROI complex subimage contrast is produced with respect to the equivalent velocity parameter space. Based on the maximum contrast principle, the desired equivalent velocity is then estimated and applied for deblurring the ROI. Finally, we can achieve the refocused SAR image of the moving target. Different from the conventional approach of moving target autofocusing that requires resynthesizing back to the full data from the cropped ROI data, the proposed method directly operates on the small-sized defocused ROI subimage without any resynthesizing operations. It is helpful for the computational burden reduction, procedure simplification, and clutter interference suppression. The experiments on synthetic and real data are carried out to validate the effectiveness of the proposed method. Index Terms-Ground moving target, region of interest (ROI), synthetic aperture radar (SAR). 0196-2892

Dynamic hand gesture recognition is of great importance for human-computer interaction. In this paper, we present a method to discriminate the four kinds of dynamic hand gestures, snapping fingers, flipping fingers, hand rotation and calling, using a radar micro-Doppler sensor. Two micro-Doppler features are extracted from the time-frequency spectrum and the support vector machine is used to classify these four kinds of gestures. The experimental results on measured data demonstrate that the proposed method can produce a classification accuracy higher than 88.56%.

Range and velocity estimation of moving targets using conventional stepped-frequency pulse radar may suffer from the range-Doppler coupling and the phase wrapping. To overcome these problems, this paper presents a new radar waveform named multiple stepped-frequency pulse trains and proposes a new algorithm. It is shown that by using multiple stepped-frequency pulse trains and the robust phase unwrapping theorem (RPUT), both of the range-Doppler coupling and the phase wrapping can be robustly resolved, and accordingly, the range and the velocity of a moving target can be accurately estimated.