ID 原文 译文
17125 同时，针对实际应用过程中可能出现的信标节点阵型不佳的情况，采用了改进的Tikhonov正则化方法，根据目标函数变化情况反馈控制正则化参数，消除了雅可比矩阵不满秩对迭代过程的影响。 At the same time, considering the situation that the beacon nodearray may not be good in the practical application, an improved Tikhonov regularization method is adopted tocontrol the regularization parameters according to the feedback of the iterative effect, which can compensatethe influence of the singular Jacobian matrix on the objective function.
17126 通过仿真分析，验证了该文算法的有效性。 The effectiveness of the proposedalgorithm in this paper is verified by simulation analysis.
17127 大多数传统的合成孔径雷达(SAR)目标识别方法仅仅使用了单一的幅度特征，但是由于斑点噪声的存在，仅仅使用幅度特征会限制识别的性能。 In most of Synthetic Aperture Radar (SAR) target recognition methods, only the amplitude feature,i.e., intensity of pixels, is used to recognize targets. Nevertheless, due to the speckle noise, only using theamplitude feature will affect the recognition performance.
17128 为了进一步提高SAR目标识别的性能，该文提出了一个基于深度森林的多级特征融合SAR目标识别方法。 For further improving the recognition performance, inthis paper, a novel multi-level feature fusion target recognition method based on deep forest for SAR images isproposed.
17129 首先，在特征提取阶段，提取了多级幅度特征和多级密集尺度不变特征变换(Dense-SIFT)特征。 At First, in the feature extraction step, two kinds of features, i.e., the multi-level amplitude feature and the multi-level Dense Scale-Invariant Feature Transform (Dense-SIFT) feature are extracted.
17130 幅度特征反映了目标反射强度，Dense-SIFT特征描述了目标的结构特征。 The amplitude feature describes intensity information and the Dense-SIFT feature describes structure information.
17131 而多级特征可以从局部到全局表征目标。 Furthermore, for each feature, its corresponding multi-level features are extracted to represent target information from local to global.
17132 随后，为了更完整、充分地反映SAR目标信息，借鉴深度森林的思想对多级幅度特征和多级Dense-SIFT特征进行联合利用。 Then, for reflecting target information more comprehensive and sufficient, the multi-level amplitude feature and the multi-level Dense-SIFT feature are jointly utilized profiting from the idea of deep forest.
17133 一方面通过堆叠的方式不断将多级幅度特征和多级Dense-SIFT特征进行融合，另一方面通过逐层的特征变换挖掘深层信息。 On the one hand, the cascade structure can fusion multi-level amplitude feature and the multi-level Dense-SIFT feature steadily. On the other hand, the deep feature representation can be mined by layer-by-layer feature transformation.
17134 最后利用得到的深层融合特征对目标进行识别任务。 Finally, the fusion feature is used to recognize targets.