《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (11): 3581-3586.DOI: 10.11772/j.issn.1001-9081.2023101540

• 多媒体计算与计算机仿真 • 上一篇    下一篇

基于模糊多尺度特征的遥感图像分割网络

李子怡, 曲婷婷, 崇乾鹏, 徐金东()   

  1. 烟台大学 计算机与控制工程学院,山东 烟台 264005
  • 收稿日期:2023-11-09 修回日期:2023-12-25 接受日期:2023-12-26 发布日期:2024-01-04 出版日期:2024-11-10
  • 通讯作者: 徐金东
  • 作者简介:李子怡(2000—),女,山东新泰人,硕士研究生,主要研究方向:遥感图像分割、图像分类
    曲婷婷(1996—),女,山东莱州人,硕士研究生,主要研究方向:遥感图像分割
    崇乾鹏(1999—),男,山东临沂人,硕士研究生,主要研究方向:遥感图像分割、计算机视觉、机器学习
  • 基金资助:
    国家自然科学基金资助项目(62072391)

Remote sensing image segmentation network based on fuzzy multiscale features

Ziyi LI, Tingting QU, Qianpeng CHONG, Jindong XU()   

  1. School of Computer and Control Engineering,Yantai University,Yantai Shandong 264005,China
  • Received:2023-11-09 Revised:2023-12-25 Accepted:2023-12-26 Online:2024-01-04 Published:2024-11-10
  • Contact: Jindong XU
  • About author:LI Ziyi, born in 2000, M. S. candidate. Her research interests include remote sensing image segmentation, image classification.
    QU Tingting, born in 1996, M. S. candidate. Her research interests include remote sensing image segmentation.
    CHONG Qianpeng, born in 1999, M. S. candidate. His research interests include remote sensing image segmentation, computer vision, machine learning.
  • Supported by:
    National Natural Science Foundation of China(62072391)

摘要:

受成像距离、光照、地物特征、环境等因素影响,遥感图像中同一类别物体可能存在一定差异,而不同类别的物体反而显示相似的视觉特征,这导致在分割时存在着不确定性,即类内异质与类间模糊。为了解决此问题,提出一种用于遥感图像分割的模糊多尺度卷积神经网络(FMCNet)。该网络通过提取图像中不同尺度、大小和宽高比的感受野,充分表征遥感物体的细节信息,并利用模糊逻辑有效地表达像素与其相邻像素之间的关系,进而解决遥感图像分割中的不确定性问题。实验结果表明,FMCNet在ISPR Vaihingen和Potsdam数据集上的整体准确率(OA)分别为85.3%和86.3%,优于现有流行的语义分割方法。

关键词: 语义分割, 卷积神经网络, 模糊逻辑, 遥感图像, 多尺度特征

Abstract:

Affected by imaging distance, illumination, surface features, environment and other factors, objects of the same category in remote sensing images may have certain differences, while objects of different categories instead show similar visual features, which leads to uncertainty in segmentation, that is intra-class heterogeneity and inter-class ambiguity. To solve these problems, a Fuzzy Multiscale Convolutional Neural Network (FMCNet) was proposed for remote sensing image segmentation. By extracting receptive fields of different scales, sizes and aspect ratios, the detailed information in remote sensing objects was fully represented, and fuzzy logic was used to effectively express the relationship between pixels and their adjacent pixels, thus overcoming the uncertainty problem in remote sensing image segmentation. Experimental results show that the Overall Accuracy (OA) of FMCNet on ISPR Vaihingen and Potsdam datasets is 85.3% and 86.3% respectively, outperforming the existing state-of-the-art semantic segmentation methods.

Key words: semantic segmentation, convolutional neural network, fuzzy logic, remote sensing image, multiscale feature

中图分类号: