Research on Gating Fusion Algorithm for Power Grid Survey Data Based on Enhanced Mamba Spatial Neighborhood Relationship

In power grid surveying, it is often necessary to fuse panchromatic and multispectral imagery for the design of power lines. Despite the abundance of deep learning networks for fusing these images, the results often suffer from spectral information loss or structural blurring. This study introduces...

Full description

Saved in:
Bibliographic Details
Main Authors: Aiyuan Zhang, Jinguo Lv, Yu Geng, Xiaolei Wang, Xianhu Li
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/21/6980
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850062451576406016
author Aiyuan Zhang
Jinguo Lv
Yu Geng
Xiaolei Wang
Xianhu Li
author_facet Aiyuan Zhang
Jinguo Lv
Yu Geng
Xiaolei Wang
Xianhu Li
author_sort Aiyuan Zhang
collection DOAJ
description In power grid surveying, it is often necessary to fuse panchromatic and multispectral imagery for the design of power lines. Despite the abundance of deep learning networks for fusing these images, the results often suffer from spectral information loss or structural blurring. This study introduces a fusion model specifically tailored for power grid surveying that significantly enhances the representation of spatial–spectral features in remote sensing images. The model comprises three main modules: a TransforRS-Mamba module that integrates the sequence processing capabilities of the Mamba model with the attention mechanism of the Transformer to effectively merge spatial and spectral features; an improved spatial proximity-aware attention mechanism (SPPAM) that utilizes a spatial constraint matrix to greatly enhance the recognition of complex object relationships; and an optimized spatial proximity-constrained gated fusion module (SPCGF) that integrates spatial proximity constraints with residual connections to boost the recognition accuracy of key object features. To validate the effectiveness of the proposed method, extensive comparative and ablation experiments were conducted on GF-2 satellite images and the QuickBird (QB) dataset. Both qualitative and quantitative analyses indicate that our method outperforms 11 existing methods in terms of fusion effectiveness, particularly in reducing spectral distortion and spatial detail loss. However, the model’s generalization performance across different data sources and environmental conditions has yet to be evaluated. Future research will explore the integration of various satellite datasets and assess the model’s performance in diverse environmental contexts.
format Article
id doaj-art-7e4707bf65034aecb067439976fc0c71
institution DOAJ
issn 1424-8220
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-7e4707bf65034aecb067439976fc0c712025-08-20T02:49:55ZengMDPI AGSensors1424-82202024-10-012421698010.3390/s24216980Research on Gating Fusion Algorithm for Power Grid Survey Data Based on Enhanced Mamba Spatial Neighborhood RelationshipAiyuan Zhang0Jinguo Lv1Yu Geng2Xiaolei Wang3Xianhu Li4School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaShanghai Aerospace Space Technology Co., Ltd., Shanghai 201306, ChinaIn power grid surveying, it is often necessary to fuse panchromatic and multispectral imagery for the design of power lines. Despite the abundance of deep learning networks for fusing these images, the results often suffer from spectral information loss or structural blurring. This study introduces a fusion model specifically tailored for power grid surveying that significantly enhances the representation of spatial–spectral features in remote sensing images. The model comprises three main modules: a TransforRS-Mamba module that integrates the sequence processing capabilities of the Mamba model with the attention mechanism of the Transformer to effectively merge spatial and spectral features; an improved spatial proximity-aware attention mechanism (SPPAM) that utilizes a spatial constraint matrix to greatly enhance the recognition of complex object relationships; and an optimized spatial proximity-constrained gated fusion module (SPCGF) that integrates spatial proximity constraints with residual connections to boost the recognition accuracy of key object features. To validate the effectiveness of the proposed method, extensive comparative and ablation experiments were conducted on GF-2 satellite images and the QuickBird (QB) dataset. Both qualitative and quantitative analyses indicate that our method outperforms 11 existing methods in terms of fusion effectiveness, particularly in reducing spectral distortion and spatial detail loss. However, the model’s generalization performance across different data sources and environmental conditions has yet to be evaluated. Future research will explore the integration of various satellite datasets and assess the model’s performance in diverse environmental contexts.https://www.mdpi.com/1424-8220/24/21/6980selective state space modelspatial–spectral fusionspatial proximity constraintdeep learningpower grid surveyinggated fusion
spellingShingle Aiyuan Zhang
Jinguo Lv
Yu Geng
Xiaolei Wang
Xianhu Li
Research on Gating Fusion Algorithm for Power Grid Survey Data Based on Enhanced Mamba Spatial Neighborhood Relationship
Sensors
selective state space model
spatial–spectral fusion
spatial proximity constraint
deep learning
power grid surveying
gated fusion
title Research on Gating Fusion Algorithm for Power Grid Survey Data Based on Enhanced Mamba Spatial Neighborhood Relationship
title_full Research on Gating Fusion Algorithm for Power Grid Survey Data Based on Enhanced Mamba Spatial Neighborhood Relationship
title_fullStr Research on Gating Fusion Algorithm for Power Grid Survey Data Based on Enhanced Mamba Spatial Neighborhood Relationship
title_full_unstemmed Research on Gating Fusion Algorithm for Power Grid Survey Data Based on Enhanced Mamba Spatial Neighborhood Relationship
title_short Research on Gating Fusion Algorithm for Power Grid Survey Data Based on Enhanced Mamba Spatial Neighborhood Relationship
title_sort research on gating fusion algorithm for power grid survey data based on enhanced mamba spatial neighborhood relationship
topic selective state space model
spatial–spectral fusion
spatial proximity constraint
deep learning
power grid surveying
gated fusion
url https://www.mdpi.com/1424-8220/24/21/6980
work_keys_str_mv AT aiyuanzhang researchongatingfusionalgorithmforpowergridsurveydatabasedonenhancedmambaspatialneighborhoodrelationship
AT jinguolv researchongatingfusionalgorithmforpowergridsurveydatabasedonenhancedmambaspatialneighborhoodrelationship
AT yugeng researchongatingfusionalgorithmforpowergridsurveydatabasedonenhancedmambaspatialneighborhoodrelationship
AT xiaoleiwang researchongatingfusionalgorithmforpowergridsurveydatabasedonenhancedmambaspatialneighborhoodrelationship
AT xianhuli researchongatingfusionalgorithmforpowergridsurveydatabasedonenhancedmambaspatialneighborhoodrelationship