ID 原文 译文
13094 该样本集涵盖1962个不同极化方式、分辨率以及类型的 船只样本，在此基础上开展了船只几何参数分析，以及不同分类器与特征组合的船只类型识别性能分析等面工作。 The HR!S covers 1 962 samples with different polarization modes, resolutons and sh i p types. The sh i p geometry parameters and the ship classification performance of HR!S with different classifier and features are analyzed.
13095 结果表明：RADARSAT-2在HH、VH、VV极化中提取的几何参数均优于GF-3，并且航向在VV 极化对船只几何提取影响最小。 The results indicate that the geometrcal parameters extracted from- RADARSAT-2in HH, VH and VV polarization are all better than that of GF-3. Furthermore, the dreeiion has little influence on the geometric parameter of ships in VV polarizat i on.
13096 在类型识别性能上，随机森林(random forest,RF)分类器对GF-3船只分类精度最优达到了 61. 85%，而对于RADARSAT-2的船只分类精度最优达到了60. 80% , GF-3船只分类精度优于RADARSAT-2。 In terms of ship type recognition performance! the accuracy of random forest (RF) classifier achieved 61. 85% on GF-3 data and 60. 80% on RADARSAT-2 data. In general, the classification accuracy of GF-3 ships is better than RADARS AT-2.
13097 本文所构建的HR!S不仅进ー步完善了高分辨率船只样本，并且在海上船只类型识别等方面具有的重要意义。 The HR4S constructed in this paper not only further improves the high-resolution ship samples, but also has Emportant significance in the recognition of ship types at sea.
13098 在极化合成孔径雷达(synthetic aperture radar, SAR)图像理解和解译中，地物分类是重要的应用方向之一。 In the understanding and interpretat i on of polarimetric synthetic aperture radar (PolSAR) mages, terran classificaton is one of the most mportant applicatons.
13099 为了研究多角度极化/AR图像的地物分类，文中基于极化统计特征差异性顺序，给出了多角度极化分解特征序列构建方法。 The paper studes the terran classification of muli-angle polarimetrc SAR images based on non-analytic scattering models. The feature mode2 decomposes muti-angle polarimetric SAR images by three decomposition methods to obtain characteristic parameters, and finally classifies.
13100 首先，采用基于Wishart分布的统计量对非各向同性散射中心进行检测，并逐像素生成基于散射特征差异的新序列图像。 First, we quantify and rank media polarimetric scattering dissimilarity over all aspects.
13101 然后，面向多种极化特征分解模型，提出通用的多角度极化特征一阶差分序列描述方法及编码方法，包括Yamaguchi四分量分解、Krogager分解以及H/A/Alpha分解，得到多维特征参数序列。 In addition, for the muti-polarization feature decomposition model, a general multi-angle polarization feature first-order difference sequence description method and coding method are proposed, including Yamaguchi four-component decomposition, Krogager decomposition and H/A/Alpha decomposton, whch are decomposed to obtain multE-dEmensonal characterstc parameters.
13102 最后，通过两种方法对比后最终选用支持向量机(support vector machine, SVM)方法对特征序列进行分类。 Finally, the feature sequences are classified by support vector machines(SVM).
13103 通过机载V波段极化/AR开展360°观测试验，验证了该方法的有效性，并展示出在地物分类方面的应用潜力。 The 360-degree observaton experiment of Pband polarimetric SAR is carried out to verify the effectiveness of the method and reveal the application potential in the terram classification of features.