ID	原文	译文
54397	复杂背景下雷达微弱目标检测一直以来是雷达信号处理领域的国际性难题，	Radar weak target detection under complex background has always been a worldwide difficult problem in the field of radar signal processing.
54398	随着雷达新体制的发展，给信号处理提供了更多的空间维度，	With the development of novel radar system, more spatial dimensions can be provided for signal processing.
54399	正交波形MIMO雷达的宽发窄收观测方式可有效延长目标驻留时间、实现时域、空域和频率的联合处理和高分辨估计，从而有利于积累目标能量和抑制杂波，提高强杂波背景中弱小目标检测能力。	Orthogonal waveform multiple-input-multiple-output(MIMO) radar's wide-transmission and narrow-reception with ubiquitous observation can effectively extend the dwell time of the target. It can realize the joint signal processing in the time, space, and frequency domain, and high-resolution estimation, thereby helping to accumulate target's energy and suppress clutter, which can improve the ability for weak and small targets detection in strong clutter background.
54400	本文对近年来正交波形MIMO雷达长时间积累和目标检测技术的研究进展进行了归纳总结，	In view of the advantages of orthogonal waveform MIMO radar, the recent research progress of long-time integration and target detection technology are summarized in this paper.
54401	介绍了正交波形MIMO雷达长时积累的概念和分类，	The concept and classification of orthogonal waveform MIMO radar long-time integration are introduced.
54402	并从机动目标回波特性认知、变换域相参积累、检测前跟踪、长时间相参积累、稀疏时频分析等方面给出了正交波形MIMO雷达机动目标积累的有效途径。	Effective solutions of maneuvering targets integration using orthogonal waveform MIMO radar are provided from the aspects of characteristics of maneuvering target, transform domain coherent integration, tracking-before-detection, long-time coherent integration, and sparse time-frequency analysis etc.
54403	最后，该文总结了现有研究存在的问题，对未来关注的技术发展进行了展望。	Finally, the problems in the existing research are summarized, and the future development of technology is provided as well.
54404	随着深度学习技术的迅猛发展，卷积神经网络(Convolutional Neural Networks，CNN)在合成孔径雷达(Synthetic Aperture Radar，SAR)舰船分类任务上取得很高的精度。	With the rapid development of deep learning technology, CNN has got great accuracy in SAR ship classification. However, because of the character of SAR picture and the fragility of CNN, the performance of CNN is unstable that causes hidden danger in practical application.
54405	但同时，由于SAR成像存在相干斑噪声等特性以及CNN自身的脆弱性，使得预测结果稳定性较差，在实际应用中存在明显隐患。	For CNN's insufficient robustness in SAR ship identification task, this paper makes use of adversarial example to research the adversarial robustness of SAR ship identification that represent the ability of maintaining stable input-output relation under small change.
54406	本文将对抗样本引入到SAR舰船识别鲁棒性的研究之中，通过从梯度、边界、黑盒模拟等多个角度对CNN网络进行全方位的对抗攻击及干扰，	This paper use kinds of adversarial attack based on gradient, boundary, block box and so on to fool most common CNN in SAR ship identification task.