Fine-Grained Extraction of Coastal Aquaculture Ponds From Remote Sensing Images Using an Edge-Supervised Multi-task Neural Network

Precise monitoring and extraction of coastal aquaculture ponds are crucial for ecological conservation and the sustainable use of coastal wetlands. However, traditional image analysis techniques often struggle to efficiently extract aquaculture ponds in the complex, heterogeneous environments of coa...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing Vol. 18; pp. 11342 - 11357
Main Authors: Qi, Jian, Ji, Min, Jin, Fengxiang, Xu, Jianran, Ji, Hanyu, Wang, Juan
Format: Journal Article
Language:English
Published: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Ablation
Aquaculture
Automation
Boundaries
Coastal aquaculture ponds (CAP)
Decoding
Deep learning
Earth
edge-supervised multi-task
Feature extraction
fine-grained extraction
Image analysis
Image edge detection
Image processing
Imagery
Marine aquaculture
Multitasking
Neural networks
Optimization
Ponds
Remote sensing
remote sensing images (RSI)
Sea measurements
Sustainable use
Training
Wetlands
ISSN:1939-1404, 2151-1535
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Precise monitoring and extraction of coastal aquaculture ponds are crucial for ecological conservation and the sustainable use of coastal wetlands. However, traditional image analysis techniques often struggle to efficiently extract aquaculture ponds in the complex, heterogeneous environments of coastal wetlands. While deep learning approaches have enhanced automation, existing models are limited by their reliance on single-feature attention, which fails to capture the global structural characteristics of aquaculture ponds, such as boundaries and internal spatial relationships, thus restricting their generalization capability. To address these issues, this article introduces a novel multitask aquaculture pond extraction network (MAENet). This network facilitates the supervised extraction process by modeling pond boundaries and the distances from internal points to these boundaries. It notably enhances performance in complex environments and significantly boosts generalization capabilities by learning global structural features. First, a shared encoder-decoder architecture was constructed, leveraging large kernel depthwise separable convolution and residual optimization, thereby enhancing both local and global feature representations. Then, a selective task fusion module was developed to optimize the allocation of shared feature space, effectively alleviating the negative transfer problem of multitask architecture. Finally, the adoption of an adaptively optimized multitask loss function obviates the necessity for manual allocation of weights. Ablation and comparative experiments using GF2 imagery from the Qingdao coastal wetlands show that MAENet outperforms existing methods in complex scenarios. Furthermore, transfer experiments with JL1 imagery from Jiangmen and Yantai demonstrate the strong generalization capability of the proposed method across different environments.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2025.3561160