Highly Maneuvering Target Detection Based on Neural Network and Generalized Radon-Fourier Transform
Highly Maneuvering Target Detection Based on Neural Network and Generalized Radon-Fourier Transform
复制标题
DOI：
10.1109/lgrs.2023.3312677
复制
发表时间：
2023
影响因子：
4.8
通讯作者：
Jiachen Wang;Yifeng Wu;Xiaobo Deng;Lei Zhang;Juan Wang;Lichao Zhou
中科院分区：
文献类型：
--
作者：
Jiachen Wang;Yifeng Wu;Xiaobo Deng;Lei Zhang;Juan Wang;Lichao Zhou
高机动目标检测在相干处理间隔（CPI）内存在距离徙动（RM）和多普勒频移（DFM）问题，导致相干积累性能下降。本文提出了一种新的基于神经网络和广义Radon-Fourier变换（GRFT）的相干积分方法。具体地说，该方法开发了一个神经网络，可以推断出目标的轨迹从雷达回波，和轨迹根据一些判断标准，减少GRFT方法的参数的搜索范围。然后，通过GRFT对RM和DFM进行补偿，从而提高了相干积累的性能。此外，我们引入了一个定制的正则化损失的神经网络的发展，提高了检测性能。实验结果表明，该方法在保证相似检测性能的前提下，显著降低了计算量。
Detection of highly maneuvering targets often suffers from the problem of range migration (RM) and Doppler frequency migration (DFM) within coherent processing interval (CPI), which results in performance degradation in coherent integration. In this letter, we propose a new coherent integration method which is based on neural networks and generalized Radon-Fourier transform (GRFT). Specifically, this method develops a neural network that can infer the target trajectory from the radar echo, and the trajectory reduces the search ranges of the GRFT method’s parameters according to some judgment criteria. After that, the RM and DFM are compensated via GRFT, and thereby it improves the performance of coherent integration. Besides, we introduce a customized regularization loss into the development of the neural network, which improves the detection performance. The superiority of the proposed method over GRFT is that it reduces the computational cost significantly with similar detection performance, which is confirmed by the results of experiments.