首页> 外文期刊>Geoscience and Remote Sensing Letters, IEEE >Land-Use Classification via Extreme Learning Classifier Based on Deep Convolutional Features
【24h】

Land-Use Classification via Extreme Learning Classifier Based on Deep Convolutional Features

机译:基于深度卷积特征的极限学习分类器的土地利用分类

获取原文
获取原文并翻译 | 示例
           

摘要

One of the challenging issues in high-resolution remote sensing images is classifying land-use scenes with high quality and accuracy. An effective feature extractor and classifier can boost classification accuracy in scene classification. This letter proposes a deep-learning-based classification method, which combines convolutional neural networks (CNNs) and extreme learning machine (ELM) to improve classification performance. A pretrained CNN is initially used to learn deep and robust features. However, the generalization ability is finite and suboptimal, because the traditional CNN adopts fully connected layers as classifier. We use an ELM classifier with the CNN-learned features instead of the fully connected layers of CNN to obtain excellent results. The effectiveness of the proposed method is tested on the UC-Merced data set that has 2100 remotely sensed land-use-scene images with 21 categories. Experimental results show that the proposed CNN-ELM classification method achieves satisfactory results.
机译:高分辨率遥感影像中具有挑战性的问题之一是对土地使用场景进行高质量和准确的分类。有效的特征提取器和分类器可以提高场景分类中的分类精度。这封信提出了一种基于深度学习的分类方法,该方法结合了卷积神经网络(CNN)和极限学习机(ELM)来提高分类性能。预训练的CNN最初用于学习深度和强大的功能。但是,由于传统的CNN采用完全连接的层作为分类器,因此泛化能力有限且次优。我们使用具有CNN学习功能的ELM分类器来代替CNN的完全连接层,以获得出色的结果。该方法的有效性在UC-Merced数据集上进行了测试,该数据集包含2100个具有21个类别的遥感土地使用现场图像。实验结果表明,所提出的CNN-ELM分类方法取得了令人满意的结果。

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