HiSTENet: History-Integrated Spatial–Temporal Information Extraction Network for Time Series Remote Sensing Image Change Detection

Time series remote sensing images (TSIs) offer essential data for time series remote sensing image change detection with remote sensing technology advances. However, most existing methods focus on bi-temporal images, lacking the exploration of temporal information between images. This presents a sig...

Full description

Saved in:
Bibliographic Details
Main Authors: Lu Zhao, Ling Wan, Lei Ma, Yiming Zhang
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/5/792
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850222782386798592
author Lu Zhao
Ling Wan
Lei Ma
Yiming Zhang
author_facet Lu Zhao
Ling Wan
Lei Ma
Yiming Zhang
author_sort Lu Zhao
collection DOAJ
description Time series remote sensing images (TSIs) offer essential data for time series remote sensing image change detection with remote sensing technology advances. However, most existing methods focus on bi-temporal images, lacking the exploration of temporal information between images. This presents a significant challenge in effectively utilizing the rich spatio-temporal and object information inherent to TSIs. In this work, we propose a History-Integrated Spatial–Temporal Information Extraction Network (HiSTENet), which comprehensively utilize the spatio-temporal information of TSIs to achieve change detection of continuous image pairs. A Spatial-Temporal Relationship Extraction Module is utilized to model the spatio-temporal relationship. Simultaneously, a Historical Integration Module is introduced to fuse the objects’ characteristics across historical temporal images, while leveraging the features of historical images. Furthermore, the Feature Alignment Fusion Module mitigates pseudo changes by computing feature offsets and aligning images in the feature space. Experiments on SpaceNet7 and DynamicEarthNet demonstrate that HiSTENet outperforms other representative methods, achieving a better balance between precision and recall.
format Article
id doaj-art-1aa9520d47484a77bf182df055c5e9d1
institution OA Journals
issn 2072-4292
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-1aa9520d47484a77bf182df055c5e9d12025-08-20T02:06:13ZengMDPI AGRemote Sensing2072-42922025-02-0117579210.3390/rs17050792HiSTENet: History-Integrated Spatial–Temporal Information Extraction Network for Time Series Remote Sensing Image Change DetectionLu Zhao0Ling Wan1Lei Ma2Yiming Zhang3Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaBeijing Institute of Remote Sensing Information, Beijing 100011, ChinaTime series remote sensing images (TSIs) offer essential data for time series remote sensing image change detection with remote sensing technology advances. However, most existing methods focus on bi-temporal images, lacking the exploration of temporal information between images. This presents a significant challenge in effectively utilizing the rich spatio-temporal and object information inherent to TSIs. In this work, we propose a History-Integrated Spatial–Temporal Information Extraction Network (HiSTENet), which comprehensively utilize the spatio-temporal information of TSIs to achieve change detection of continuous image pairs. A Spatial-Temporal Relationship Extraction Module is utilized to model the spatio-temporal relationship. Simultaneously, a Historical Integration Module is introduced to fuse the objects’ characteristics across historical temporal images, while leveraging the features of historical images. Furthermore, the Feature Alignment Fusion Module mitigates pseudo changes by computing feature offsets and aligning images in the feature space. Experiments on SpaceNet7 and DynamicEarthNet demonstrate that HiSTENet outperforms other representative methods, achieving a better balance between precision and recall.https://www.mdpi.com/2072-4292/17/5/792time series remote sensing imagestime series remote sensing images change detectionspatial–temporal relationshipfeature fusiondeep learning
spellingShingle Lu Zhao
Ling Wan
Lei Ma
Yiming Zhang
HiSTENet: History-Integrated Spatial–Temporal Information Extraction Network for Time Series Remote Sensing Image Change Detection
Remote Sensing
time series remote sensing images
time series remote sensing images change detection
spatial–temporal relationship
feature fusion
deep learning
title HiSTENet: History-Integrated Spatial–Temporal Information Extraction Network for Time Series Remote Sensing Image Change Detection
title_full HiSTENet: History-Integrated Spatial–Temporal Information Extraction Network for Time Series Remote Sensing Image Change Detection
title_fullStr HiSTENet: History-Integrated Spatial–Temporal Information Extraction Network for Time Series Remote Sensing Image Change Detection
title_full_unstemmed HiSTENet: History-Integrated Spatial–Temporal Information Extraction Network for Time Series Remote Sensing Image Change Detection
title_short HiSTENet: History-Integrated Spatial–Temporal Information Extraction Network for Time Series Remote Sensing Image Change Detection
title_sort histenet history integrated spatial temporal information extraction network for time series remote sensing image change detection
topic time series remote sensing images
time series remote sensing images change detection
spatial–temporal relationship
feature fusion
deep learning
url https://www.mdpi.com/2072-4292/17/5/792
work_keys_str_mv AT luzhao histenethistoryintegratedspatialtemporalinformationextractionnetworkfortimeseriesremotesensingimagechangedetection
AT lingwan histenethistoryintegratedspatialtemporalinformationextractionnetworkfortimeseriesremotesensingimagechangedetection
AT leima histenethistoryintegratedspatialtemporalinformationextractionnetworkfortimeseriesremotesensingimagechangedetection
AT yimingzhang histenethistoryintegratedspatialtemporalinformationextractionnetworkfortimeseriesremotesensingimagechangedetection