生成对抗学习式半监督遥感影像生成网络地图方法
DOI:
作者:
作者单位:

1.国防科技大学电子科学学院;2.军事科学院国防科技创新研究院

作者简介:

通讯作者:

中图分类号:

P283.8

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


Online Map Generation Method from Remote Sensing Images via Semi-supervised Adversarial Learning
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    现有遥感影像生成网络地图方法中,多为全监督学习模型或者无监督学习模型。针对现有全监督学习获取精确配对样本耗费资源问题,同时兼顾网络地图生成质量,提出了一种新颖的基于生成对抗网络的半监督网络地图生成模型,旨在利用少量精确配对的数据和大量非配对数据,实现智能化遥感影像直接生成为网络地图。此外设计了基于变换一致性正则化和样本增强一致性的半监督学习策略,克服了非精确配对数据带来的不一致性问题,同时能获得更好的模型泛化性能。对不同地图数据集进行了充分的对比实验,验证了半监督网络地图生成方法的有效性和快速性。

    Abstract:

    In the field of online maps generation based on remote sensing images, the most common method is based on the fully supervised learning or unsupervised learning. To address the problems of the resource-consuming problem challenge and poor generation quality, this paper proposed a novel semi-supervised map generation model based on generative adversarial networks, which aims to transform remote sensing images to online maps directly by using only a few precisely matched data and a large amount of unpaired data. In addition, we designed a semi-supervised learning strategy based on transformation consistency regularization and data enhanced consistency, which overcomes the inconsistency problem caused by imprecise paired data and derives better generalization performance of the model. Adequate comparison experiments were conducted on different map datasets, which validate the semi-supervised method proposed in this paper as an effective and fast map generation tool.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-05-11
  • 最后修改日期:2024-11-20
  • 录用日期:2024-11-26
  • 在线发布日期:
  • 出版日期:
文章二维码