ID	原文	译文
54417	基于LSTM序列预测的目标检测方法通过用海杂波信号幅度时间序列对网络进行训练，再用训练后的网络对后续序列进行预测，并与后续实测信号进行比较，实现目标检测。	The target detection method based on LSTM sequence prediction uses the sea clutter signal amplitude time series to train the network, and then uses the trained network to predict subsequent sequences, and compares it with subsequently measured signals to achieve target detection.
54418	基于CNN序列分类的目标检测方法中采用截取的海杂波信号和目标信号幅度序列作为数据集样本，对一维卷积核CNN进行训练，使其具有识别目标杂波信号特征能力，从而实现目标检测。	In the target detection method based on CNN sequence classification, the intercepted sea clutter signal and the target signal amplitude sequence are used as dataset samples to train the one-dimensional convolution kernel CNN so that it can identify the target clutter signal feature, thereby achieving the target detection.
54419	最后，采用IPIX和CSIR实测海杂波数据对两种方法进行验证，结果表明两种方法均可实现一维序列信号中海面目标的检测，但LSTM预测方法对于长序列检测的实时性有待于进一步提高;	Finally, the two methods were verified using IPIX and CSIR measured sea clutter data. The results show that both methods can detect sea-surface targets in one-dimensional sequence signals, but the real-time performance of LSTM prediction methods for long sequence detection needs to be further improved.
54420	CNN分类方法可实现实时检测，但仅利用信号幅度信息，检测性能仍需进一步提升。	CNN classification method can realize real-time detection, but using only signal amplitude information, the detection performance still needs to be further improved.
54421	合成孔径雷达(Synthetic Aperture Radar，SAR)因为全天候、全天时的观测能力在军事和民用领域有着广泛的应用背景。	Synthetic Aperture Radar(SAR) has a wide range of applications in military and civil fields because of its all-weather and all-time observation capabilities.
54422	考虑到SAR研究的成本和效率以及SAR图像在目标检测领域的应用，SAR图像的仿真技术发挥了重要优势。	Considering the cost and efficiency of SAR research and the application of SAR image in the field of target detection, the simulation technology of SAR image plays an important role.
54423	针对传统成像方法耗时较长的问题，本文利用基于弹跳射线法(SBR)的快速成像技术以达到快速获取大批量SAR图像的目的。	Aiming at the problem that the traditional imaging method takes a long time, this paper uses the fast imaging technology based on the Shooting and Bouncing Ray(SBR) to achieve the purpose of quickly obtaining a large number of SAR images.
54424	为了更加精准地识别SAR图像中的目标，在Faster RCNN目标检测网络的基础上，根据真实舰船目标的尺寸改变候选框的初始尺寸以及利用特征融合的方式对原算法架构加以改进。	In order to recognize the target in SAR image more accurately, based on the Faster RCNN network, the initial size of anchor is changed according to the size of real ship target, and the original algorithm architecture is improved by feature fusion.
54425	最后，在Faster RCNN框架中加入特征金字塔结构(Feature pyramid networks，FPN)，进一步提高算法对SAR图像中的舰船目标检测和识别的能力。	Finally, feature pyramid networks(FPN) is added to the Faster RCNN network to further improve the ability of detecting and recognizing warship targets in SAR images.
54426	天发船收高频雷达系统中，由于电离层随机扰动和接收船六维摆动运动影响，目标回波空时谱发生展宽和形变，严重影响雷达探测性能。	The space-time spectrum of target echoes are broadened and deformed in a shipborne high frequency radar via hybrid sky-surface wave propagation, which seriously affects the radar detection performance, due to the influence of the ionospheric random perturbation and the six degree of freedom motion of the receiving ship.