STWANet: Spatio-Temporal Wavelet Attention Aggregation Network for Remote Sensing Change Detection

Existing change detection techniques exhibit significant deficiencies in the recognition of building edges and detailed textures, making it challenging to accurately distinguish building boundaries from the background. Consequently, these methods struggle to precisely capture complex building contou...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyang Zhang, Kaihui Dong, Dapeng Cheng, Zhen Hua, Jinjiang Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10924762/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762116523786240
author Xiaoyang Zhang
Kaihui Dong
Dapeng Cheng
Zhen Hua
Jinjiang Li
author_facet Xiaoyang Zhang
Kaihui Dong
Dapeng Cheng
Zhen Hua
Jinjiang Li
author_sort Xiaoyang Zhang
collection DOAJ
description Existing change detection techniques exhibit significant deficiencies in the recognition of building edges and detailed textures, making it challenging to accurately distinguish building boundaries from the background. Consequently, these methods struggle to precisely capture complex building contours and subtle texture variations. To address this problem, a spatio-temporal wavelet attention aggregation network (STWANet) is proposed in this article. This network uses a pretrained Resnet18 to extract multiscale features to obtain features with sufficient spatial details and semantic information. We introduce the spatio-temporal differential self-attention module to extract the spatio-temporal difference information between two multiscale temporal features, and the introduction of the self-Attention mechanism is able to focus on the regions with the most significant changes in the multiscale feature maps. In order to extract the changes of detailed features such as building edges, we introduce the wavelet feature enhancement module (WFEM) to enhance the representation of the frequency domain feature information of the changing features, especially the enhancement of high-frequency detail information (e.g., building edges). In order to make up for the shortcomings of WFEM in capturing specific details and global spatial features, we also introduce the dual attention aggregation module to extract the feature information of the changing areas in parallel with WFEM, which can process the spatial context information in a more detailed way, and can better retain the detailed features, especially the complex spatial structure and shape information. spatial structure and shape information. We verify the effectiveness and advancement of STWANet on three classical datasets (LEVIR-CD, WHU-CD, GZ-CD), and the experimental results show that STWANet reaches the state-of-the-art performance level.
format Article
id doaj-art-aebaff624e9b416a8a6c9849d637f672
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-aebaff624e9b416a8a6c9849d637f6722025-08-20T03:05:49ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01188813883010.1109/JSTARS.2025.355109310924762STWANet: Spatio-Temporal Wavelet Attention Aggregation Network for Remote Sensing Change DetectionXiaoyang Zhang0Kaihui Dong1Dapeng Cheng2https://orcid.org/0009-0003-4408-5114Zhen Hua3https://orcid.org/0000-0003-1638-2974Jinjiang Li4https://orcid.org/0000-0002-2080-8678School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, ChinaSchool of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaSchool of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaExisting change detection techniques exhibit significant deficiencies in the recognition of building edges and detailed textures, making it challenging to accurately distinguish building boundaries from the background. Consequently, these methods struggle to precisely capture complex building contours and subtle texture variations. To address this problem, a spatio-temporal wavelet attention aggregation network (STWANet) is proposed in this article. This network uses a pretrained Resnet18 to extract multiscale features to obtain features with sufficient spatial details and semantic information. We introduce the spatio-temporal differential self-attention module to extract the spatio-temporal difference information between two multiscale temporal features, and the introduction of the self-Attention mechanism is able to focus on the regions with the most significant changes in the multiscale feature maps. In order to extract the changes of detailed features such as building edges, we introduce the wavelet feature enhancement module (WFEM) to enhance the representation of the frequency domain feature information of the changing features, especially the enhancement of high-frequency detail information (e.g., building edges). In order to make up for the shortcomings of WFEM in capturing specific details and global spatial features, we also introduce the dual attention aggregation module to extract the feature information of the changing areas in parallel with WFEM, which can process the spatial context information in a more detailed way, and can better retain the detailed features, especially the complex spatial structure and shape information. spatial structure and shape information. We verify the effectiveness and advancement of STWANet on three classical datasets (LEVIR-CD, WHU-CD, GZ-CD), and the experimental results show that STWANet reaches the state-of-the-art performance level.https://ieeexplore.ieee.org/document/10924762/Attention mechanismchange detectionfrequency domain featuresremote sensingwavelet transform
spellingShingle Xiaoyang Zhang
Kaihui Dong
Dapeng Cheng
Zhen Hua
Jinjiang Li
STWANet: Spatio-Temporal Wavelet Attention Aggregation Network for Remote Sensing Change Detection
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Attention mechanism
change detection
frequency domain features
remote sensing
wavelet transform
title STWANet: Spatio-Temporal Wavelet Attention Aggregation Network for Remote Sensing Change Detection
title_full STWANet: Spatio-Temporal Wavelet Attention Aggregation Network for Remote Sensing Change Detection
title_fullStr STWANet: Spatio-Temporal Wavelet Attention Aggregation Network for Remote Sensing Change Detection
title_full_unstemmed STWANet: Spatio-Temporal Wavelet Attention Aggregation Network for Remote Sensing Change Detection
title_short STWANet: Spatio-Temporal Wavelet Attention Aggregation Network for Remote Sensing Change Detection
title_sort stwanet spatio temporal wavelet attention aggregation network for remote sensing change detection
topic Attention mechanism
change detection
frequency domain features
remote sensing
wavelet transform
url https://ieeexplore.ieee.org/document/10924762/
work_keys_str_mv AT xiaoyangzhang stwanetspatiotemporalwaveletattentionaggregationnetworkforremotesensingchangedetection
AT kaihuidong stwanetspatiotemporalwaveletattentionaggregationnetworkforremotesensingchangedetection
AT dapengcheng stwanetspatiotemporalwaveletattentionaggregationnetworkforremotesensingchangedetection
AT zhenhua stwanetspatiotemporalwaveletattentionaggregationnetworkforremotesensingchangedetection
AT jinjiangli stwanetspatiotemporalwaveletattentionaggregationnetworkforremotesensingchangedetection