• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences >EVALUATING A CONVOLUTIONAL NEURAL NETWORK FOR FEATURE EXTRACTION AND TREE SPECIES CLASSIFICATION USING UAV-HYPERSPECTRAL IMAGES
【24h】

EVALUATING A CONVOLUTIONAL NEURAL NETWORK FOR FEATURE EXTRACTION AND TREE SPECIES CLASSIFICATION USING UAV-HYPERSPECTRAL IMAGES

机译：使用无人机 - 超光谱图像评估用于特征提取和树种分类的卷积神经网络

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced feature extraction and classification methods. Different from the traditional feature extraction methods, that highly depend on user’s knowledge, the convolutional neural network (CNN)-based method can automatically learn and extract the spatial-related features layer by layer. However, in order to capture significant features of the data, the CNN classifier requires a large number of training samples, which are hardly available when dealing with tree species in tropical forests. This study investigated the following topics concerning the classification of 14 tree species in a subtropical forest area of Southern Brazil: i) the performance of the CNN method associated with a previous step to increase and balance the sample set (data augmentation) for tree species classification as compared to the conventional machine learning methods support vector machine (SVM) and random forest (RF) using the original training data; ii) the performance of the SVM and RF classifiers when associated with a data augmentation step and spatial features extracted from a CNN. Results showed that the CNN classifier outperformed the conventional SVM and RF classifiers, reaching an overall accuracy (OA) of 84.37% and Kappa of 0.82. The SVM and RF had a poor accuracy with the original spectral bands (OA 62.67% and 59.24%) but presented an increase between 14% and 21% in OA when associated with a data augmentation and spatial features extracted from a CNN.
机译：树种的分类可以显着受益于由与先进特征提取和分类方法相关联的无人航空车辆（UAV）获取的高空间和光谱信息。与传统的特征提取方法不同，这高度依赖于用户的知识，卷积神经网络（CNN）的方法可以自动学习并通过图层提取空间相关的特征层。然而，为了捕获数据的显着特征，CNN分类器需要大量的训练样本，在处理热带森林中的树种时几乎没有可用。本研究调查了对巴西南部亚热带林区14种树种分类的以下主题：i）CNN方法与前一步的CNN方法的表现增加，以增加和平衡树种分类的样本集（数据增强）与传统的机器学习方法相比，使用原始训练数据支持向量机（SVM）和随机林（RF）; ii）与从CNN中提取的数据增强步骤和空间特征相关联时SVM和RF分类器的性能。结果表明，CNN分类器优于传统的SVM和RF分类器，达到84.37％和κ0.82的总精度（OA）。 SVM和RF与原始光谱带（OA 62.67％和59.24％）具有较差的准确性，但是当与从CNN中提取的数据增强和空间特征相关联时，OA中的14％至21％的增加。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号