How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classif...How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.展开更多
精细的田块数据是现代农业的重要基础资料,该研究针对从高分辨率遥感影像中提取田块精细数据的需求,建立了一种先验知识融合语义特征的冬小麦田块精细提取方法(prior knowledge and semantic features integration-based farmland parce...精细的田块数据是现代农业的重要基础资料,该研究针对从高分辨率遥感影像中提取田块精细数据的需求,建立了一种先验知识融合语义特征的冬小麦田块精细提取方法(prior knowledge and semantic features integration-based farmland parcel extraction methodology,PKFFPE),PKFFPE以遥感图像和相应的边缘图像作为输入,采用编码器-解码器结构进行特征提取,利用多尺度注意力模块捕获不同尺度的关键特征,使用SoftMax对图像进行初步分割;通过深入分析同一田块内颜色、纹理等特征的分布规律获取先验知识,利用先验知识建立后处理方法,对初分割结果进行优化,生成田块精细数据。选择河北省邯郸市馆陶县和山东省泰安市宁阳县作为试验区,用于验证PKFFPE方法在平原地区和丘陵地区的适用性;选择UNet、ErfNet、SegNet、EIGNet,以及面向对象分类的方法作为初分割的对比方法,选择条件随机场和形态学处理作为的后处理的对比方法开展对比试验。试验结果表明,PKFFPE方法在馆陶县、宁阳县结果的准确率(96.1%、93.2%)、精确率(90.6%、87.6%)、召回率(93.2%、90.6%)、和F1分数(91.9%,89.0%)均优于对比方法,证明了PKFFPE方法在从高分辨遥感影像中提取田块精细数据方面具有突出的优势,能够应用于科研和生产实践。展开更多
复杂场景分类是遥感图像解译的一项重要内容。本文通过优化ResNet18深度残差网络和随机森林,实现了遥感图像复杂场景的高精度分类。首先通过数据扩充将数据库扩充以缓解因训练样本少带来的过拟合问题,然后采用ResNet18深度残差网络自动...复杂场景分类是遥感图像解译的一项重要内容。本文通过优化ResNet18深度残差网络和随机森林,实现了遥感图像复杂场景的高精度分类。首先通过数据扩充将数据库扩充以缓解因训练样本少带来的过拟合问题,然后采用ResNet18深度残差网络自动提取遥感图像场景特征,最后使用随机森林分类器实现复杂场景分类任务并分别在NWPU-RESISC45和UC Merced Land Use数据库上进行了实验。结果表明,本文模型场景分类准确率分别为98.86%和99.17%,与单独使用ResNet18深度残差网络相比,本文模型分类准确率分别提高3.36%和1.71%,相比于其他场景分类方法,本文模型分类准确率分别提高5.23%和1.55%。展开更多
基金supported by the National Natural Science Foundation of China(U1435220)
文摘How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.
文摘精细的田块数据是现代农业的重要基础资料,该研究针对从高分辨率遥感影像中提取田块精细数据的需求,建立了一种先验知识融合语义特征的冬小麦田块精细提取方法(prior knowledge and semantic features integration-based farmland parcel extraction methodology,PKFFPE),PKFFPE以遥感图像和相应的边缘图像作为输入,采用编码器-解码器结构进行特征提取,利用多尺度注意力模块捕获不同尺度的关键特征,使用SoftMax对图像进行初步分割;通过深入分析同一田块内颜色、纹理等特征的分布规律获取先验知识,利用先验知识建立后处理方法,对初分割结果进行优化,生成田块精细数据。选择河北省邯郸市馆陶县和山东省泰安市宁阳县作为试验区,用于验证PKFFPE方法在平原地区和丘陵地区的适用性;选择UNet、ErfNet、SegNet、EIGNet,以及面向对象分类的方法作为初分割的对比方法,选择条件随机场和形态学处理作为的后处理的对比方法开展对比试验。试验结果表明,PKFFPE方法在馆陶县、宁阳县结果的准确率(96.1%、93.2%)、精确率(90.6%、87.6%)、召回率(93.2%、90.6%)、和F1分数(91.9%,89.0%)均优于对比方法,证明了PKFFPE方法在从高分辨遥感影像中提取田块精细数据方面具有突出的优势,能够应用于科研和生产实践。
文摘复杂场景分类是遥感图像解译的一项重要内容。本文通过优化ResNet18深度残差网络和随机森林,实现了遥感图像复杂场景的高精度分类。首先通过数据扩充将数据库扩充以缓解因训练样本少带来的过拟合问题,然后采用ResNet18深度残差网络自动提取遥感图像场景特征,最后使用随机森林分类器实现复杂场景分类任务并分别在NWPU-RESISC45和UC Merced Land Use数据库上进行了实验。结果表明,本文模型场景分类准确率分别为98.86%和99.17%,与单独使用ResNet18深度残差网络相比,本文模型分类准确率分别提高3.36%和1.71%,相比于其他场景分类方法,本文模型分类准确率分别提高5.23%和1.55%。
