Semantic segmentation of remote sensing images based on multiscale features and global information modeling

文献类型： 外文期刊

第一作者： Gao, Yupeng

作者： Gao, Yupeng;Luo, Xiaoling;Gao, Xiaojing;Pan, Xin;Fu, Xueliang;Gao, Yupeng;Luo, Xiaoling;Gao, Xiaojing;Pan, Xin;Fu, Xueliang;Yan, Weihong

作者机构：

关键词： Multiscale features; Global modeling information; Remote sensing image; Semantic segmentation

期刊名称：EXPERT SYSTEMS WITH APPLICATIONS （ 影响因子：8.5； 五年影响因子：8.3 ）

ISSN： 0957-4174

年卷期： 2024 年 249 卷

页码：

收录情况： SCI

摘要： The main difficulties in semantic segmentation of remote sensing images include the effect of shadows, the blurring of feature differences between categories, and loss of small-scale category features during processing. To deal with these challenges, we propose a semantic segmentation network for RSI based on multi -scale features and global information modeling. A skillfully designed two -branch fusion attention based on an adaptive fusion converter is added to the multilevel cascaded HRNet structure to better combine multiscale features and global modeling information. Prior to this, " Coordinate attention " was combined with " Spatial attention " designed in this paper to form a Feed -forward Attention Layer (FAL) to encode finer feature information cues. Meanwhile, a more refined multilayer decoder is designed to obtain better image category recovery. Various experiments were conducted on four different scenarios and types of datasets including WHDLD, Potsdam, Vaihingen, and LoveDa, and in terms of the significant evaluation metric MIOU, with dividing the training, validation, and test sets in the ratio of 6:2:2, the performance of our model on the above four datasets was obtained with 61.79%, 70.79%, 81.15%, and 52.55%.In addition, a comparison with other excellent works is made and the results show that our designed model has better performance.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序