Region-Guided and Dual Attention Discriminative Learning Network for Hyperspectral Target Detection

ZHONG Jia-ping; LI Yun-song; XIE Wei-ying; LEI Jie; Paolo Gamba

doi:10.12263/DZXB.20221126

您当前的位置：

首页 >

文章列表页 >

Region-Guided and Dual Attention Discriminative Learning Network for Hyperspectral Target Detection

PAPERS | 更新时间：2025-12-11

- Region-Guided and Dual Attention Discriminative Learning Network for Hyperspectral Target Detection
- ACTA ELECTRONICA SINICA Vol. 52, Issue 5, Pages: 1716-1729(2024)
- 作者机构：
  
  1.西安电子科技大学综合业务网全国重点实验室，陕西西安 710071
  2.帕维亚大学，意大利帕维亚 27100
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62121001;U22B2014);The Young Elite Scientist Sponsorship Program by the China Association for Science and Technology(2020QNRC001)
- DOI：10.12263/DZXB.20221126
  CLC： TP183;TP751.1
- Received：14 September 2022，
  
  Revised：2023-04-16，
  
  Published：25 May 2024
- 稿件说明：
移动端阅览
钟佳平, 李云松, 谢卫莹, 等. 结合区域引导和双注意力机制的高光谱目标检测判别式学习网络[J]. 电子学报, 2024, 52(05): 1716-1729.

ZHONG Jia-ping, LI Yun-song, XIE Wei-ying, et al. Region-Guided and Dual Attention Discriminative Learning Network for Hyperspectral Target Detection[J]. Acta Electronica Sinica, 2024, 52(05): 1716-1729.
钟佳平, 李云松, 谢卫莹, 等. 结合区域引导和双注意力机制的高光谱目标检测判别式学习网络[J]. 电子学报, 2024, 52(05): 1716-1729. DOI：10.12263/DZXB.20221126

ZHONG Jia-ping, LI Yun-song, XIE Wei-ying, et al. Region-Guided and Dual Attention Discriminative Learning Network for Hyperspectral Target Detection[J]. Acta Electronica Sinica, 2024, 52(05): 1716-1729. DOI：10.12263/DZXB.20221126

摘要

高光谱图像（HyperSpectral Images，HSIs）具有高光谱分辨率和丰富的光谱信息，其具有的大量窄波段电磁波有利于获取感兴趣目标的理化信息，并根据对应的光谱特征对不同物质进行有效区分，从而完成目标检测任务.然而有限样本、少量先验信息、高维相似背景及不同类别差异小所导致的目标和背景混淆问题使得高光谱目标检测（Hyperspectral Target Detection，HTD）面临挑战.为此，本文提出结合区域引导和双注意力机制的高光谱目标检测判别式学习网络（Region-guided and dual-Attention Discriminative learning Network，RADN），以缓解标记样本少的条件下不同类别相似度高和相同类别差异性大导致的背景和目标不易区分的问题，减少高维冗余特征带来的计算复杂度，同时提升检测精度.本文使用经验性区域引导网络训练，采用光谱约束的无监督聚类方法确定网络输入，选择性地关注高光谱图像中的显著性特征和感兴趣区域.此外，本文在网络中添加双通道注意力机制来辅助复杂背景分布的估计，并在网络中引入不同类别光谱先验损失函数，进一步减少高维复杂背景以及光谱变化对于目标的干扰.实验结果和分析表明，RADN在不同数据集上的性能优于现有先进的算法.

Abstract

Hyperspectral images (HSIs) have high spectral resolution and rich spectral information

which can obtain the physical and chemical information of the target of interest by using a large number of narrow-band waves. HSIs can effectively distinguish different substances by corresponding spectral features

and complete the task of target detection. However

the problem of target and background confusion caused by limited samples

a small amount of prior information

high dimensional similar background

and differences between different classes make hyperspectral target detection (HTD) still face challenges. To this end

we propose a region-guided and dual-attention discriminative learning network (RADN) for HTD to solve the problem of intra-class differences and inter-class similarities under a few samples. It can reduce the computational complexity caused by high-dimensional redundant features and improve detection accuracy. In this paper

we introduce the empirical region-guided network for training. We employ the spectrally constrained unsupervised clustering network to determine the network input. To selectively focus on salient features and regions of interest

we add a dual-channel attention mechanism in the generator and discriminator to assist in the estimation of complex background distributions; We introduce an inter-class spectral prior loss function in the network and further reduce the interference of high-dimensional complex background and spectral changes to the target. Experimental results and analysis show that RADN outperforms existing state-of-the-art algorithms on different datasets.

关键词

Keywords

references

童庆禧 , 张兵 , 张立福 . 中国高光谱遥感的前沿进展 [J ] . 遥感学报 , 2016 , 20 ( 5 ): 689 - 707 .

TONG Q X , ZHANG B , ZHANG L F . Current progress of hyperspectral remote sensing in China [J ] . Journal of Remote Sensing , 2016 , 20 ( 5 ): 689 - 707 . (in Chinese)

CHANG C I . Hyperspectral target detection: Hypothesis testing, signal-to-noise ratio, and spectral angle theories [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 3069716 .

张良培 . 高光谱目标探测的进展与前沿问题 [J ] . 武汉大学学报(信息科学版) , 2014 , 39 ( 12 ): 1387 - 1394, 1400 .

ZHANG L P . Advance and future challenges in hyperspectral target detection [J ] . Geomatics and Information Science of Wuhan University , 2014 , 39 ( 12 ): 1387 - 1394, 1400 . (in Chinese)

DONG Y N , SHI W Z , DU B , et al . Asymmetric weighted logistic metric learning for hyperspectral target detection [J ] . IEEE Transactions on Cybernetics , 2022 , 52 ( 10 ): 11093 - 11106 .

ZARE A , JIAO C Z , GLENN T . Discriminative multiple instance hyperspectral target characterization [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 , 40 ( 10 ): 2342 - 2354 .

YANG X C , DONG M Z , WANG Z Y , et al . Data-augmented matched subspace detector for hyperspectral subpixel target detection [J ] . Pattern Recognition , 2020 , 106 : 107464 .

贺霖 , 潘泉 , 邸韡 , 等 . 高光谱图像目标检测研究进展 [J ] . 电子学报 , 2009 , 37 ( 9 ): 2016 - 2024 .

HE L , PAN Q , DI W , et al . Research advance on target detection for hyperspectral imagery [J ] . Acta Electronica Sinica , 2009 , 37 ( 9 ): 2016 - 2024 . (in Chinese)

CHANG C I , CHEN J . Orthogonal subspace projection using data sphering and low-rank and sparse matrix decomposition for hyperspectral target detection [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2021 , 59 ( 10 ): 8704 - 8722 .

REED I S , YU X . Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution [J ] . IEEE Transactions on Acoustics, Speech, and Signal Processing , 1990 , 38 ( 10 ): 1760 - 1770 .

JIN X Y , PASWATERS S , CLINE H . A comparative study of target detection algorithms for hyperspectral imagery [C ] // Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV . Florida : SPIE , 2009 : 682 - 693 .

HARSANYI J C , CHANG C I . Hyperspectral image classification and dimensionality reduction: An orthogonal subspace projection approach [J ] . IEEE Transactions on Geoscience and Remote Sensing , 1994 , 32 ( 4 ): 779 - 785 .

CHANG C I . Hyperspectral Data Processing: Algorithm Design and Analysis [M ] . New York : John Wiley & Sons , 2013 .

ZOU Z X , SHI Z W . Hierarchical suppression method for hyperspectral target detection [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2016 , 54 ( 1 ): 330 - 342 .

ZHAO R , SHI Z W , ZOU Z X , et al . Ensemble-based cascaded constrained energy minimization for hyperspectral target detection [J ] . Remote Sensing , 2019 , 11 ( 11 ): 1310 .

DU B , ZHANG Y X , ZHANG L P , et al . Beyond the sparsity-based target detector: A hybrid sparsity and statistics-based detector for hyperspectral images [J ] . IEEE Transactions on Image Processing , 2016 , 25 ( 11 ): 5345 - 5357 .

ZHU D H , DU B , ZHANG L P . Single-spectrum-driven binary-class sparse representation target detector for hyperspectral imagery [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2021 , 59 ( 2 ): 1487 - 1500 .

LI W , DU Q , ZHANG B . Combined sparse and collaborative representation for hyperspectral target detection [J ] . Pattern Recognition , 2015 , 48 ( 12 ): 3904 - 3916 .

QIN H N , XIE W Y , LI Y S , et al . Weakly supervised adversarial learning via latent space for hyperspectral target detection [J ] . Pattern Recognition , 2023 , 135 : 109125 .

DU J M , LI Z Y , SUN H . CNN-based target detection in hyperspectral imagery [C ] // IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium . Piscataway : IEEE , 2018 : 2761 - 2764 .

LI W , WU G D , DU Q . Transferred deep learning for hyperspectral target detection [C ] // 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) . Piscataway : IEEE , 2017 : 5177 - 5180 .

YANG X , DENG C , ZHENG F , et al . Deep spectral clustering using dual autoencoder network [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2019 : 4061 - 4070 .

ZHAO X B , LI W , ZHAO C H , et al . Hyperspectral target detection based on weighted cauchy distance graph and local adaptive collaborative representation [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 5527313 .

WANG Y L , CHEN X , WANG F C , et al . Meta-learning based hyperspectral target detection using Siamese network [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 5527913 .

WANG X X , CHEN X Y , GOU S P , et al . Hyperspectral target detection via deep multiple instance self-attention neural network [C ] // IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium . Piscataway : IEEE , 2019 : 2284 - 2287 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . Red Hook : Curran Associates Inc. , 2017 : 6000 - 6010 .

陈文俊 , 杨春玲 . 图像压缩感知的特征域优化及自注意力增强神经网络重构算法 , 电子学报 , 2022 , 50 ( 11 ): 2629 - 2637 .

CHEN W J , YANG C L . Feature-space optimization-inspired and self-attention enhanced neural network reconstruction algorithm for image compressive sensing [J ] . Acta Electonica Sinica , 2022 , 50 ( 11 ): 2629 - 2637 . (in Chinese)

朱张莉 , 饶元 , 吴渊 , 等 . 注意力机制在深度学习中的研究进展 [J ] . 中文信息学报 , 2019 , 33 ( 6 ): 1 - 11 .

ZHU Z L , RAO Y , WU Y , et al . Research progress of attention mechanism in deep learning [J ] . Journal of Chinese Information Processing , 2019 , 33 ( 6 ): 1 - 11 . (in Chinese)

HU J , SHEN L , SUN G . Squeeze-and-excitation networks [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 7132 - 7141 .

HAUT J M , PAOLETTI M E , PLAZA J , et al . Visual attention-driven hyperspectral image classification [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 10 ): 8065 - 8080 .

MEI X G , PAN E T , MA Y , et al . Spectral-spatial attention networks for hyperspectral image classification [J ] . Remote Sensing , 2019 , 11 ( 8 ): 963 .

DAI T , CAI J R , ZHANG Y B , et al . Second-order attention network for single image super-resolution [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2019 : 11057 - 11066 .

ZHANG Y L , LI K P , LI K , et al . Image super-resolution using very deep residual channel attention networks [C ] // European Conference on Computer Vision . Cham : Springer , 2018 : 294 - 310 .

PENG Y X , HE X T , ZHAO J J . Object-part attention model for fine-grained image classification [J ] . IEEE Transactions on Image Processing , 2018 , 27 ( 3 ): 1487 - 1500 .

FUKUI H , HIRAKAWA T , YAMASHITA T , et al . Attention branch network: Learning of attention mechanism for visual explanation [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2019 : 10697 - 10706 .

XIE W Y , ZHANG X , LI Y S , et al . Background learning based on target suppression constraint for hyperspectral target detection [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2020 , 13 : 5887 - 5897 .

CHIANG S S , CHANG C I , GINSBERG I W . Unsupervised target detection in hyperspectral images using projection pursuit [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2001 , 39 ( 7 ): 1380 - 1391 .

ZHU D H , DU B , ZHANG L P . Two-stream convolutional networks for hyperspectral target detection [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2021 , 59 ( 8 ): 6907 - 6921 .

KAUFMAN J R , EISMANN M T , CELENK M . Assessment of spatial-spectral feature-level fusion for hyperspectral target detection [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2015 , 8 ( 6 ): 2534 - 2544 .

LIU X W , ZHU X Z , LI M M , et al . Multiple kernel k-means with incomplete kernels [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2020 , 42 ( 5 ): 1191 - 1204 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Fast Malicious Code Detection Method Based on Feature Fusion

Multi-Branch Structure Based Local Channel Attention with Uncertainty

A Face Region Hierarchical Encryption Algorithm for Palette Images

An Unsupervised Clustering-Based Intrusion Detection Method

Related Author

SONG Ya-fei

WANG Ya-nan

WANG Shuo

WANG Jian

WU Bang-gu

ZHANG Su-lin

SHI Hong

ZHU Peng-fei

Related Institution

Air Defense and Antimissile School, Air Force Engineering University

College of Intelligence and Computing, Tianjin University

Automotive Data of China Co., Ltd.

School of Computer Science and Technology, Harbin Institute of Technology

School of Computer Science and Technology,State Key Laboratory of Software Engineering,Wuhan University

⁰