Hyperspectral Target Detection Based on Prior Spectral Perception and Local Graph Fusion

With the development of hyperspectral sensing technology, hyperspectral target detection technology plays an important role in remote target detection. However, existing hyperspectral target detection models are poorly adapted to complex backgrounds and mainly focus on the spectral domain, making le...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaobin Zhao, Jun Huang, Yunquan Gao, Qingwang Wang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10623901/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850051867991605248
author Xiaobin Zhao
Jun Huang
Yunquan Gao
Qingwang Wang
author_facet Xiaobin Zhao
Jun Huang
Yunquan Gao
Qingwang Wang
author_sort Xiaobin Zhao
collection DOAJ
description With the development of hyperspectral sensing technology, hyperspectral target detection technology plays an important role in remote target detection. However, existing hyperspectral target detection models are poorly adapted to complex backgrounds and mainly focus on the spectral domain, making less use of spatial structure information leading to low target detection rates. Therefore, a new target detection algorithm based on the prior spectral perception and local graph fusion is proposed. First, the prior spectrum-guided target extraction method is established. This method can take full advantage of the background and target spectral information by local inner and outer window linkage, reduce the impact of spectral variability on target acquisition performance, and improve detection stability. Second, the target enhancement strategy based on the Gabor multifeature graph is proposed. This technique makes full use of multidirectional and multiscale spatial information, which can reduce the influence of brightness, contrast and amplitude variation on detection performance due to light and angle. Finally, spatial–spectral fusion is executed to achieve target detection. It can make full use of spectral and spatial structure information to improve the target detection effect. Publicly available datasets and real collected datasets are adopted to check the validity of the proposed method. After comparison, it is found that the proposed algorithm has better detection effect than existing baseline methods. The maximum improvement in AUC values are 16.56%–88.16% across the eight datasets.
format Article
id doaj-art-d349c585ee3a4cbea89a622a91e37c9a
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-d349c585ee3a4cbea89a622a91e37c9a2025-08-20T02:52:59ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-0117139361394810.1109/JSTARS.2024.343956010623901Hyperspectral Target Detection Based on Prior Spectral Perception and Local Graph FusionXiaobin Zhao0https://orcid.org/0000-0002-9828-1976Jun Huang1https://orcid.org/0000-0002-2022-5747Yunquan Gao2Qingwang Wang3https://orcid.org/0000-0001-5820-5357Beijing Key Laboratory of Fractional Signals and Systems, School of Information and Electronics, Beijing Institute of Technology, Beijing, ChinaAnhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet, Anhui University of Technology, Ma'anshan, ChinaAnhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet, Anhui University of Technology, Ma'anshan, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, ChinaWith the development of hyperspectral sensing technology, hyperspectral target detection technology plays an important role in remote target detection. However, existing hyperspectral target detection models are poorly adapted to complex backgrounds and mainly focus on the spectral domain, making less use of spatial structure information leading to low target detection rates. Therefore, a new target detection algorithm based on the prior spectral perception and local graph fusion is proposed. First, the prior spectrum-guided target extraction method is established. This method can take full advantage of the background and target spectral information by local inner and outer window linkage, reduce the impact of spectral variability on target acquisition performance, and improve detection stability. Second, the target enhancement strategy based on the Gabor multifeature graph is proposed. This technique makes full use of multidirectional and multiscale spatial information, which can reduce the influence of brightness, contrast and amplitude variation on detection performance due to light and angle. Finally, spatial–spectral fusion is executed to achieve target detection. It can make full use of spectral and spatial structure information to improve the target detection effect. Publicly available datasets and real collected datasets are adopted to check the validity of the proposed method. After comparison, it is found that the proposed algorithm has better detection effect than existing baseline methods. The maximum improvement in AUC values are 16.56%–88.16% across the eight datasets.https://ieeexplore.ieee.org/document/10623901/Hyperspectral target detectionlocal graph (LG)remote sensingspatial–spectral fusionspectral perception (SP)
spellingShingle Xiaobin Zhao
Jun Huang
Yunquan Gao
Qingwang Wang
Hyperspectral Target Detection Based on Prior Spectral Perception and Local Graph Fusion
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Hyperspectral target detection
local graph (LG)
remote sensing
spatial–spectral fusion
spectral perception (SP)
title Hyperspectral Target Detection Based on Prior Spectral Perception and Local Graph Fusion
title_full Hyperspectral Target Detection Based on Prior Spectral Perception and Local Graph Fusion
title_fullStr Hyperspectral Target Detection Based on Prior Spectral Perception and Local Graph Fusion
title_full_unstemmed Hyperspectral Target Detection Based on Prior Spectral Perception and Local Graph Fusion
title_short Hyperspectral Target Detection Based on Prior Spectral Perception and Local Graph Fusion
title_sort hyperspectral target detection based on prior spectral perception and local graph fusion
topic Hyperspectral target detection
local graph (LG)
remote sensing
spatial–spectral fusion
spectral perception (SP)
url https://ieeexplore.ieee.org/document/10623901/
work_keys_str_mv AT xiaobinzhao hyperspectraltargetdetectionbasedonpriorspectralperceptionandlocalgraphfusion
AT junhuang hyperspectraltargetdetectionbasedonpriorspectralperceptionandlocalgraphfusion
AT yunquangao hyperspectraltargetdetectionbasedonpriorspectralperceptionandlocalgraphfusion
AT qingwangwang hyperspectraltargetdetectionbasedonpriorspectralperceptionandlocalgraphfusion