ID 原文 译文
19525 高分辨率遥感图像内容复杂，提取特征来准确地表达图像内容是提高检索性能的关键。 High-resolution remote sensing images have complex visual contents, and extracting feature to represent image content accurately is the key to improving image retrieval performance.
19526 卷积神经网络(CNN)迁移学习能力强，其高层特征能够有效迁移到高分辨率遥感图像中。 Convolutional Neural Networks (CNN) have strong transfer learning ability, and the high-level features of CNN can be efficiently transferred to high-resolution remote sensing images.
19527 为了充分利用高层特征的优点，该文提出一种基于高层特征图组合及池化的方法来融合不同CNN中的高层特征。 In order to make full use of the advantages of high-levelfeatures, a combination and pooling method based on high-level feature maps is proposed to fuse high-levelfeatures from different CNNs.
19528 首先将高层特征作为特殊的卷积层特征，进而在不同输入尺寸下保留高层输出的特征图；然后将不同高层输出的特征图组合成一个更大的特征图，以综合不同CNN学习到的特征； Firstly, the high-level features are adopted as special convolutional features topreserve the feature maps of the high-level outputs under different input sizes, and then the feature maps arecombined into a larger feature map to integrate the features learned by different CNNs.
19529 接着采用最大池化的方法对组合特征图进行压缩，提取特征图中的显著特征； The combined featuremap is compressed by max-pooling method to extract salient features.
19530 最后，采用主成分分析(PCA)来降低显著特征的冗余度。 Finally, the Principal ComponentAnalysis (PCA) is utilized to reduce the redundancy of the salient features.
19531 实验结果表明，与现有检索方法相比，该方法提取的特征在检索效率和准确率上都有优势。 The experimental results show that compared with the existing retrieval methods, the features extracted by this method have advantages in retrieval efficiency and precision.
19532 水下无线传感网络(UWSN)执行目标跟踪时，因为各个传感器节点测量值对目标状态估计的贡献不一样以及节点能量有限，所以探索一种好的节点融合权重方法和节点规划机制能够获得更好的跟踪性能。 When the Underwater Wireless Sensor Network (UWSN) performs target tracking, the contributions of the measured values of the nodes are different, and the battery energy carried by the sensor node is limited.Therefore, a good node fusion weight method and node planning mechanism can obtain better tracking performance.
19533 针对上述问题，该文提出一种基于Grubbs准则和互信息熵加权融合的分布式粒子滤波(PF)目标跟踪算法(GMIEW)。 A distributed particle filter target tracking algorithm based on Grubbs criterion and MutualInformation Entropy Weighted (GMIEW) fusion is proposed to solve the above problem in this paper.
19534 首先利用Grubbs准则对传感器节点所获得的信息进行分析检验，去除干扰信息和错误信息。 Firstly,the Grubbs criterion is used to analyze and verify the information obtained by the sensor nodes before theinformation fusion, and the interference information and error information are removed.