RaHFF-Net: Recall-Adjustable Hierarchical Feature Fusion Network for Remote Sensing Image Change Detection

Remote sensing (RS) image change detection (CD) aims to identify areas of interest that have changed between bitemporal images. For complex scenarios (e.g., varying lighting conditions), the diverse shapes and scales of the changed areas is especially vulnerable to cause CD models to suffer from ser...

Full description

Saved in:
Bibliographic Details
Main Authors: Bin Wang, Kang Zhao, Tong Xiao, Pinle Qin, Jianchao Zeng
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/10733986/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846156571224047616
author Bin Wang
Kang Zhao
Tong Xiao
Pinle Qin
Jianchao Zeng
author_facet Bin Wang
Kang Zhao
Tong Xiao
Pinle Qin
Jianchao Zeng
author_sort Bin Wang
collection DOAJ
description Remote sensing (RS) image change detection (CD) aims to identify areas of interest that have changed between bitemporal images. For complex scenarios (e.g., varying lighting conditions), the diverse shapes and scales of the changed areas is especially vulnerable to cause CD models to suffer from serious missed detections. To address aforementioned problem, we propose a high recall multiscale feature fusion model for RS change interpretation. Initially, the RaHFF-Net extracts hierarchical multiscale feature from bitemporal RS images; Then, it employs CNN and Transformer to effectively merge local and global information across same-scale, cross-scale, and multiscale features. Finally, to address the issue of instance imbalance in CD, a novel hyperexpectation push pull loss regularization term is proposed. This loss function is designed to elevate the expected predictions of positive instances across the dataset, thereby enabling the development of a deep learning model with a high recall rate.
format Article
id doaj-art-fc971e66707b4c7eb6b263e0be6f5c5b
institution Kabale University
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-fc971e66707b4c7eb6b263e0be6f5c5b2024-11-26T00:00:16ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-011817619010.1109/JSTARS.2024.348568710733986RaHFF-Net: Recall-Adjustable Hierarchical Feature Fusion Network for Remote Sensing Image Change DetectionBin Wang0https://orcid.org/0000-0002-3372-7906Kang Zhao1https://orcid.org/0009-0006-5342-7376Tong Xiao2https://orcid.org/0009-0009-3626-5186Pinle Qin3https://orcid.org/0000-0002-9086-7366Jianchao Zeng4https://orcid.org/0000-0001-7755-7550Department of Computer Science and Technology, North University of China, Taiyuan, ChinaDepartment of Computer Science and Technology, North University of China, Taiyuan, ChinaDepartment of Computer Science and Technology, North University of China, Taiyuan, ChinaDepartment of Computer Science and Technology, North University of China, Taiyuan, ChinaDepartment of Computer Science and Technology, North University of China, Taiyuan, ChinaRemote sensing (RS) image change detection (CD) aims to identify areas of interest that have changed between bitemporal images. For complex scenarios (e.g., varying lighting conditions), the diverse shapes and scales of the changed areas is especially vulnerable to cause CD models to suffer from serious missed detections. To address aforementioned problem, we propose a high recall multiscale feature fusion model for RS change interpretation. Initially, the RaHFF-Net extracts hierarchical multiscale feature from bitemporal RS images; Then, it employs CNN and Transformer to effectively merge local and global information across same-scale, cross-scale, and multiscale features. Finally, to address the issue of instance imbalance in CD, a novel hyperexpectation push pull loss regularization term is proposed. This loss function is designed to elevate the expected predictions of positive instances across the dataset, thereby enabling the development of a deep learning model with a high recall rate.https://ieeexplore.ieee.org/document/10733986/Change detection (CD)hyperexpectation push pull (HEPP) lossmultiscale feature fusiontransformer
spellingShingle Bin Wang
Kang Zhao
Tong Xiao
Pinle Qin
Jianchao Zeng
RaHFF-Net: Recall-Adjustable Hierarchical Feature Fusion Network for Remote Sensing Image Change Detection
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Change detection (CD)
hyperexpectation push pull (HEPP) loss
multiscale feature fusion
transformer
title RaHFF-Net: Recall-Adjustable Hierarchical Feature Fusion Network for Remote Sensing Image Change Detection
title_full RaHFF-Net: Recall-Adjustable Hierarchical Feature Fusion Network for Remote Sensing Image Change Detection
title_fullStr RaHFF-Net: Recall-Adjustable Hierarchical Feature Fusion Network for Remote Sensing Image Change Detection
title_full_unstemmed RaHFF-Net: Recall-Adjustable Hierarchical Feature Fusion Network for Remote Sensing Image Change Detection
title_short RaHFF-Net: Recall-Adjustable Hierarchical Feature Fusion Network for Remote Sensing Image Change Detection
title_sort rahff net recall adjustable hierarchical feature fusion network for remote sensing image change detection
topic Change detection (CD)
hyperexpectation push pull (HEPP) loss
multiscale feature fusion
transformer
url https://ieeexplore.ieee.org/document/10733986/
work_keys_str_mv AT binwang rahffnetrecalladjustablehierarchicalfeaturefusionnetworkforremotesensingimagechangedetection
AT kangzhao rahffnetrecalladjustablehierarchicalfeaturefusionnetworkforremotesensingimagechangedetection
AT tongxiao rahffnetrecalladjustablehierarchicalfeaturefusionnetworkforremotesensingimagechangedetection
AT pinleqin rahffnetrecalladjustablehierarchicalfeaturefusionnetworkforremotesensingimagechangedetection
AT jianchaozeng rahffnetrecalladjustablehierarchicalfeaturefusionnetworkforremotesensingimagechangedetection