ID 原文 译文
13464 然后根据更新后的字典动态计算稀疏度。 Next, the sparsity is dynamically calculated according to the information of each dictionary update.
13465 最后依据最小重构误差准则实现SAR目标识别。 Finally, the SAR target recognition is achieved by minimizing the reconstruction error.
13466 在公开数据集MSTAR上的仿真实验结果表明,该方法提取到的特征信息可分度高,对SAR目标的识别具有较好的性能. The simulation results on MSTAR data sets show that the feature information extracted by this method can be highly indexed and has better performance on SAR target recognition.
13467 通过自适应小波变换分离活动部件及目标,剔除活动部件对成像结果的影响；提取清晰的散射中心,然后基于逆合成孔径雷达(inverse synthetic aperture radar, ISAR)图像灰度级不连续点寻找区域边界,将目标点和背景分离,采用自适应边界收敛方法对目标区域进行轮廓特征提取,得到了良好的目标轮廓特征。 Firstly, the adaptive wavelet transform is performed to separate the signal parameters of moving parts from the target's. Then, based on the discontinuity point of image gray scale, the target is separated from the background. Finally, an adaptive boundary convergence method is used to extract the contour features of the target region, and a good contour feature is obtained.
13468 采用实测数据对方法进行了验证. The effectiveness and stability of the proposed algorithm is verified by measured data.
13469 逆合成孔径雷达(inverse synthetic aperture radar, ISAR)对非合作目标做成像时图像质量依赖于对目标运动参数的准确估计。 The success of inverse synthetic aperture radar(ISAR) imaging for non-cooperative target depends on accurate estimation of relative motion parameter, especially the rotation parameters.
13470 针对在稀疏孔径和非均匀转动条件下现存的参数估计方法计算量过大或者方法适用条件不满足,提出了一种基于神经网络的参数估计方法。 In sparse aperture and larger rotation angle configuration, the existing methods suffer too much computation or applicable condition violation.
13471 此方法以成像问题的模型知识指导数据的生成过程,然后训练通用的神经网络,最终实现将数据中隐含的知识转化为转动估计器。 In this paper, a neural network based method is proposed to estimate the rotation parameters and it transforms the expertise hidden in the echo data generated based on the expert knowledge to the final estimator via the training process.
13472 从仿真实验结果来看,所得到的网络对满足一定信噪比要求的回波数据可以提供较准确的估计,所得参数可以帮助成像算法提高聚焦效果,大量的样例表明网络可以部分学习到回波与转动之间的关系。 The experimental results that the net can provide accurate estimation for echo data with appropriate SNR and the estimated parameters can help to improve the focus of imaging algorithm. Lots of examples have illustrated that the network can recognize the essential relation between the echo and the rotation motion partially.
13473 针对复杂的有限大频率选择表面(frequency selective surface, FSS)结构阐述了一种改进的非重叠和非共型的体面积分方程区域分解方法(volume-surface integral equation domain decomposition method, VSIE-DDM)。 Ths paper descrbes an mproved non-overlapp ng and non-conformal volume-surface nte- gral equation domain decomposition method (VSIE-DDM) for the complex finite frequency selecton surface (FSS) structures.