Abstract
Classifying space targets from debris is critical for radar resource management as well as rapid response during the mid-course phase of space target flight. Due to advances in deep learning techniques, various approaches have been studied to classify space targets by using micro-Doppler signatures. Previous studies have only used micro-Doppler signatures such as spectrogram and cadence velocity diagram (CVD), but in this paper, we propose a method to generate micro-Doppler signatures taking into account the relative incident angle that a radar can obtain during the target tracking process. The AlexNet and ResNet-18 networks, which are representative convolutional neural network architectures, are transfer-learned using two types of datasets constructed using the proposed and conventional signatures to classify six classes of space targets and a debris–cone, rounded cone, cone with empennages, cylinder, curved plate, and square plate. Among the proposed signatures, the spectrogram had lower classification accuracy than the conventional spectrogram, but the classification accuracy increased from 88.97% to 92.11% for CVD. Furthermore, when recalculated not with six classes but simply with only two classes of precessing space targets and tumbling debris, the proposed spectrogram and CVD show the classification accuracy of over 99.82% for both AlexNet and ResNet-18. Specially, for two classes, CVD provided results with higher accuracy than the spectrogram.
Highlights
The ballistic missile defense (BMD) system aims at detecting, tracking, classifying, and intercepting space targets
We proposed a method to generate a micro-Doppler signature considering the incident angle
Based on the principle that the micro-Doppler frequency shift appears differently depending on the angle between the direction of rotation by precession, which is the main micro-motion of the space targets, and the RLOS, it is proposed to show the constant amount of micro-Doppler frequency shift by the relative incident angle
Summary
The ballistic missile defense (BMD) system aims at detecting, tracking, classifying, and intercepting space targets. To classify space targets during the mid-course phase, which is the longest flying possible to extract fixed and accurate scattering centers at high frequencies where the target time among three phases, early studies have mainly focused on modeling various microis large compared to the wavelength, but it is difficult to extract dominant scattering centers motions such as precession, nutation, and spin [6,7,8,9,10,11,12]. Has introduced a complex-valued coordinate attention network-based end-to-end recognition method, whose input data are complex-valued echo data These CNN models have the advantage of being able to quickly create datasets and train and classify them because the process of transforming echo data to micro-Doppler signatures is not required. We generate micro-Doppler signature images considering the relative incident angle and show that the proposed signatures can improve the classification accuracy in a common CNN model
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have