SANet: A Sea-Land Segmentation Network Via Adaptive Multiscale Feature Learning

Sea-land segmentation of remote sensing images is of great significance to the dynamic monitoring of coastlines. However, the types of objects in the coastal zone are complex, and their spectra, textures, shapes, and distribution features are different. Therefore, sea-land segmentation for various t...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing 2021, Vol.14, p.116-126
Main Authors: Cui, Binge, Jing, Wei, Huang, Ling, Li, Zhongrui, Lu, Yan
Format: Article
Language:English
Subjects:
Adaptation models
Adaptive learning
atrous convolution
Boundaries
Coastal zone
Coastal zones
Coasts
Codec
Coders
Convolution
Feature extraction
Feature maps
Image processing
Image segmentation
Machine learning
Modules
Remote sensing
remote sensing image
residual block
sea–land segmentation
Semantic segmentation
Semantics
squeeze-excitation module
Task analysis
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:Sea-land segmentation of remote sensing images is of great significance to the dynamic monitoring of coastlines. However, the types of objects in the coastal zone are complex, and their spectra, textures, shapes, and distribution features are different. Therefore, sea-land segmentation for various types of coastlines is still a challenging task. In this article, a scale-adaptive semantic segmentation network, called SANet, is proposed for sea-land segmentation of remote sensing images. SANet has made two innovations on the basis of the classic encoder-decoder structure. First, to integrate the spectral, textural, and semantic features of ground objects at different scales, we designed an adaptive multiscale feature learning module (AML) to replace the conventional serial convolution operation. The AML module mainly contains a multiscale feature extraction unit and an adaptive feature fusion unit. The former can capture the multiscale detailed information and contextual semantic information of objects from an early stage, while the latter can adaptively fuse feature maps of different scales. Second, we adopted the squeeze-and-excitation module to bridge the corresponding layers of the codec so that SANet can selectively emphasize the features of the weak sea-land boundaries. Experiments on a set of Gaofen-1 remote sensing images demonstrated that SANet achieved more accurate segmentation results and obtained sharper boundaries than other methods for various natural and artificial coastlines.
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2020.3040176