ID 原文 译文
40126 但是传统的高光谱影像地物分类方法多着重于光谱维度的特征提取，却忽略了空间维度上的特征，进而影响了分类的准确性。 However, the traditional hyperspectral image classification methods mostly focus on the feature extraction of spectral dimension, but ignore the features of spatial dimension, which affects the accuracy of classification.
40127 三维卷积神经网络（Three-dimensional convolutional neural network，3D-CNN）可以同时在3个维度上对数据进行卷积处理，故本文采用3D-CNN深度网络进行高光谱影像地物分类，并针对3D-CNN网络存在的问题，提出了一种基于改进的3D-CNN的高光谱遥感影像地物分类方法。 The three-dimensional convolutional neural network(3 D-CNN)can convolute data in three dimensions at the same time, so this paper uses 3 DCNN depth network to classify ground objects with hyperspectral images, and proposes an improved algorithm based on 3 D-CNN for hyperspectral remote sensing land-cover classification.
40128 本文方法对提取到的空间和光谱特征实现融合复用，尽可能发挥特征的价值。 The method can reuse the extracted spatial and spectral features and give full play to the value of features.
40129 此外，本文引入浅层特征细节保存网络的思想，提出一种综合浅层特征细节保存的影像分类深度网络模型，进一步提高了高光谱影像地物分类的准确度。 In addition, this paper introduces the idea of shallow feature preservation network, and proposes a depth network model of image classification integrating shallow feature preservation, which further improves the accuracy of hyperspectral remote sensing land-cover classification.
40130 在Tensorflow框架下对2个常用的高光谱遥感影像数据集（Indian Pines和Pavia University）的实验结果表明，相比基础的3D-CNN网络，本文方法的分类精度提高了近2%，而且类别边界更准确。 Experimental results of two commonly used hyperspectral remote sensing image data sets(Indian Pines and Pavia University)under the framework of Tensorflow show that compared with the basic 3 D-CNN network, the classification accuracy of the proposed method is improved by nearly 2%.
40131 针对大厚比的复杂结构件数字射线成像（Digital radiography，DR），单一透照能量不能完整体现全部信息的问题，提出一种基于区域特征的脉冲耦合神经网络（Pulse coupled neural network，PCNN）多幅图像融合算法。 Aiming at the problem that single transillumination energy cannot completely cover all the information for the digital radiography(DR)of complex structures with large thickness ratios, we propose a pulse coupled neural network(PCNN)image fusion algorithm based on regional characteristics and take aero-engine turbine blades as the research objects.
40132 以航空发动机涡轮叶片为研究对象，首先在获取多幅递增管电压透照子图基础上，经非下采样轮廓波变换（Non-subsampled contourlet transform，NSCT）分解为一个低频子带和多个尺度下的高频子带； First, the multiple incremental tube voltage transillumination sub-images are decomposed into low frequency sub-bands and high frequency sub-bands at multiple scales by the non-sub-sampled contourlet transform(NSCT).
40133 其次采用PCNN算法，用各子带的改进空间频率中方向特征最明显的分量调整连接强度； Second, the PCNN algorithm is deployed to adjust the connection strength of the directions that hold the most obvious characteristics in the improved spatial frequency of each sub-band.
40134 然后低频子带采用区域均方差、高频子带采用改进的拉普拉斯能量和作为外部激励，点火映射图的判决遵循取大原则； Third, to fulfill the external excitation, the low-frequency sub-bands are calculated by the regional mean square error, while the high-frequency sub-band by the summodified Laplacian.
40135 最后通过NSCT逆变换得到融合结果图。 Thus the two results are processed through the fire mapping by following the maximum principle. Finally, the fusion images are obtained by the NSCT inverse transformation.