Abstract

Semantic segmentation of remote sensing imagery (RSI) is critical in many domains due to the diverse landscapes and different sizes of geo-objects that RSI contains, making semantic segmentation challenging. In this paper, a convolutional network, named Adaptive Feature Fusion UNet (AFF-UNet), is proposed to optimize the semantic segmentation performance. The model has three key aspects: (1) dense skip connections architecture and an adaptive feature fusion module that adaptively weighs different levels of feature maps to achieve adaptive feature fusion, (2) a channel attention convolution block that obtains the relationship between different channels using a tailored configuration, and (3) a spatial attention module that obtains the relationship between different positions. AFF-UNet was evaluated on two public RSI datasets and was quantitatively and qualitatively compared with other models. Results from the Potsdam dataset showed that the proposed model achieved an increase of 1.09% over DeepLabv3 + in terms of the average F1 score and a 0.99% improvement in overall accuracy. The visual qualitative results also demonstrated a reduction in confusion of object classes, better performance in segmenting different sizes of object classes, and better object integrity. Therefore, the proposed AFF-UNet model optimizes the accuracy of RSI semantic segmentation.

Details

Title
A deep learning method for optimizing semantic segmentation accuracy of remote sensing images based on improved UNet
Author
Wang, Xiaolei 1 ; Hu, Zirong 2 ; Shi, Shouhai 2 ; Hou, Mei 2 ; Xu, Lei 3 ; Zhang, Xiang 4 

 Zhengzhou University, The School of Geoscience and Technology, Zhengzhou, China (GRID:grid.207374.5) (ISNI:0000 0001 2189 3846); Zhengzhou University, Joint Laboratory of Eco-Meteorology, Zhengzhou University, Chinese Academy of Meteorological Sciences, Zhengzhou, China (GRID:grid.207374.5) (ISNI:0000 0001 2189 3846); SongShan Laboratory, Zhengzhou, China (GRID:grid.207374.5) 
 Zhengzhou University, The School of Geoscience and Technology, Zhengzhou, China (GRID:grid.207374.5) (ISNI:0000 0001 2189 3846) 
 China University of Geosciences (Wuhan), National Engineering Research Center for Geographic Information System, School of Geography and Information Engineering, Wuhan, China (GRID:grid.503241.1) (ISNI:0000 0004 1760 9015) 
 China University of Geosciences (Wuhan), National Engineering Research Center for Geographic Information System, School of Geography and Information Engineering, Wuhan, China (GRID:grid.503241.1) (ISNI:0000 0004 1760 9015); SongShan Laboratory, Zhengzhou, China (GRID:grid.503241.1) 
Pages
7600
Publication year
2023
Publication date
2023
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2811791627
Copyright
© The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.