...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Building and Environment >High spatial-resolution classification of urban surfaces using a deep learning method
【24h】

High spatial-resolution classification of urban surfaces using a deep learning method

机译：利用深层学习方法的城市表面的高空间分辨率分类

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Urban surface composition is key information for global carbon emission estimation, mesoscale numerical simulations, and outdoor environment studies at both city and neighborhood scales. High spatial-resolution satellite imagery can provide accurate urban surface data. Due to the large volume of data, it is timeconsuming to extract manually information from satellite imagery or use other conventional classification methods. Deep leaning-based classification methods have great potential in satellite imaginary recognition due to their high efficiency and accuracy. In this study, we established a novel workflow for deep learning-based satellite imagery classification. At the stage of training dataset preparation, an object-based image analysis (OBIA) classification with the assistance of open source ancillary data from OpenStreetMap (OSM), i.e., OBIA-OSM method, was proposed to accelerate the procedure and improve the accuracy. An area of 33.5 km2 training dataset with 1 m spatial resolution was built based on the Gaofen2 satellite imagery of Hangzhou, China (GF2-HZ dataset). A Res-UNet + inception model was developed for the deep learning process. The results using the newly built model were compared with those from previous FCN and UNet models. The overall accuracy of our proposed model on the GF2-HZ dataset reached 83.1% which outperforms previous models. The influences of raw data-related factors, such as spectral bands composition and spatial resolution, were carefully tested. Data normalization and 'transfer learning' techniques were also analyzed and applied to improve the generalization ability of deep learning models.
机译：城市表面构成是全球碳排放估计，Messcore数值模拟和户外环境研究的关键信息，包括城市和邻里鳞片。高空间分辨率卫星图像可以提供精确的城市表面数据。由于数据量大，它是从卫星图像手动提取信息的时间，或者使用其他传统的分类方法。由于其高效率和准确性，基于深度倾斜的分类方法具有很大的卫星虚构识别潜力。在这项研究中，我们建立了基于深度学习的卫星图像分类的新工作流程。在训练数据集准备的阶段，提出了一种基于对象的图像分析（OBIA）分类来自OpenStreetMap（OSM），即Obia-OSM方法的开源辅助数据，即Obia-OSM方法，以加速程序并提高准确性。基于杭州杭州（GF2-HZ数据集）的高芬2卫星图像，建立了33.5 km2培训数据集。为深度学习过程开发了Res-Unet + Inception模型。将使用新建模型的结果与来自以前的FCN和UNET模型的结果进行比较。我们在GF2-Hz数据集中提出模型的总体准确性达到了83.1％，以至于以前的型号。仔细测试了原始数据相关因素的影响，例如光谱带组成和空间分辨率。还分析了数据标准化和“转移学习”技术，并应用了改善深度学习模型的泛化能力。

著录项

  • 来源
    《Building and Environment》 |2021年第8期|107949.1-107949.13|共13页
  • 作者

    Fan Yifan; Ding Xiaotian; Wu Jindong; Ge Jian; Li Yuguo;

  • 作者单位

    Zhejiang Univ Coll Civil Engn & Architecture Hangzhou Peoples R China|Zhejiang Univ Ctr Balance Architecture Hangzhou Peoples R China;

    Zhejiang Univ Coll Civil Engn & Architecture Hangzhou Peoples R China;

    Zhejiang Univ Coll Civil Engn & Architecture Hangzhou Peoples R China;

    Zhejiang Univ Coll Civil Engn & Architecture Hangzhou Peoples R China;

    Univ Hong Kong Dept Mech Engn Hong Kong Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Urban surface recognition; Remote sensing; High spatial resolution; Deep learning;

    机译：城市表面识别;遥感;高空间分辨率;深入学习;

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