Lake water body extraction of optical remote sensing images based on semantic segmentation

Automatically extract lake water bodies of optical remote sensing images is a very challenging task, because there are many small lakes in such images, these small lakes have the characteristics of weak target information and are easily interfered by noise information. Regarding above problems, this...

Full description

Saved in:
Bibliographic Details
Published in:Applied intelligence (Dordrecht, Netherlands) Netherlands), 2022-12, Vol.52 (15), p.17974-17989
Main Authors: Zhong, Hai-Feng, Sun, Hong-Mei, Han, Dong-Nuo, Li, Zeng-Hu, Jia, Rui-Sheng
Format: Article
Language:English
Subjects:
Artificial Intelligence
Boundaries
Coders
Computer Science
Encoders-Decoders
Image segmentation
Lakes
Machines
Manufacturing
Mechanical Engineering
Modules
Performance indices
Processes
Remote sensing
Sampling
Semantic segmentation
Semantics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automatically extract lake water bodies of optical remote sensing images is a very challenging task, because there are many small lakes in such images, these small lakes have the characteristics of weak target information and are easily interfered by noise information. Regarding above problems, this paper proposes an automatic extraction method of lake water based on semantic segmentation. Firstly, a multi-scale information enhancement network is designed based on the encoder-decoder structure, and the deep dilation residual structure is used in the encoder module of the network to improve the network’s ability to mine the deep feature information and the context information of the lake water bodies. Secondly, the two-way channel attention mechanism is introduced into the network, which can reduce the interference of noise information on the lake boundaries and improve the accuracy of the network to the lake boundaries segmentation. Finally, the up-sampling convolution operation is used in the decoder module of the network to reduce the information loss during the up-sampling process. In this paper, the performance of the designed network is tested by using remote sensing images of lakes of different map scales and various evaluation indexes. The experimental results show that the designed network has better segmentation accuracy than other semantic segmentation networks.
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-022-03345-2