端到端分布式联合优化的空谱自编码密度估计模型

马纪涛; 谢卫莹; 雷杰; 方乐缘; 李云松

doi:10.12263/DZXB.20220516

您当前的位置：

首页 >

文章列表页 >

端到端分布式联合优化的空谱自编码密度估计模型

学术论文 | 更新时间：2025-12-08

- 端到端分布式联合优化的空谱自编码密度估计模型
- End-to-End Spectral-Spatial Cooperative Autoencoding Density Estimation Model
- 电子学报 2023年51卷第4期页码：1006-1020
- 作者机构：
  
  1.西安电子科技大学综合业务网理论及关键技术国家重点实验室,陕西西安 710071
  2.湖南大学电气与信息工程学院,湖南长沙 410082
- 作者简介：
  
  [ "马纪涛男，1999年出生，河北邢台人.2021年本科毕业于西安电子科技大学通信工程专业.现为西安电子科技大学信息与通信工程专业硕博连读生.主要研究方向为高光谱遥感图像异常检测及分布式深度学习.E-mail: 21011210271@stu.xidian.edu.cn" ]
  [ "谢卫莹（通讯作者）女，1988年出生，甘肃白银人.现为西安电子科技大学副教授、博导.主要研究方向为高光谱遥感图像处理、分布式智能解译以及轻量化实现.中国电子学会会员编号：E190022673M. Email: wyxie@xidian.edu.cn " ]
- 基金信息：
  
  国家自然科学基金(62121001;U22B2014);中国科协青年人才托举工程(2020QNRC001)
- DOI：10.12263/DZXB.20220516
  中图分类号： TP183;TP751.1
- 收稿：2022-05-09，
  
  修回：2022-09-05，
  
  纸质出版：2023-04-25
- 稿件说明：
移动端阅览
马纪涛,谢卫莹,雷杰等.端到端分布式联合优化的空谱自编码密度估计模型[J].电子学报,2023,51(04):1006-1020.

MA Ji-tao,XIE Wei-ying,LEI Jie,et al.End-to-End Spectral-Spatial Cooperative Autoencoding Density Estimation Model[J].ACTA ELECTRONICA SINICA,2023,51(04):1006-1020.
马纪涛,谢卫莹,雷杰等.端到端分布式联合优化的空谱自编码密度估计模型[J].电子学报,2023,51(04):1006-1020. DOI： 10.12263/DZXB.20220516.

MA Ji-tao,XIE Wei-ying,LEI Jie,et al.End-to-End Spectral-Spatial Cooperative Autoencoding Density Estimation Model[J].ACTA ELECTRONICA SINICA,2023,51(04):1006-1020. DOI： 10.12263/DZXB.20220516.

摘要

高光谱图像（Hyperspectral Image，HSI）由于其丰富的光谱信息和空间信息，被广泛应用于异常检测任务，在对地观测和深空探测中起到了重要作用.然而，现有的基于密度估计的高光谱异常检测（Hyperspectral Anomaly Detection，HAD）方法存在如下问题：一是没有联合优化概率密度估计和特征表示这两个不同的目标函数，导致深度神经网络无法学习到更加准确的概率密度函数和包含HSI固有信息的低维表示；二是缺乏高层次空间语义信息与低维流行中光谱信息的自适应融合.此外，随着光谱成像技术的发展，卫星或无人机所获取的HSI的体积越来越大，在遥感大数据的背景下，传统框架处理HSI变得十分困难，给HAD带来了极大的挑战.本文分别从以上问题出发，提出了端到端联合优化的空谱协同自编码密度估计（End-to-End Spectral-Spatial Cooperative Autoencoding Density Estimation，E2E-SSCADE）模型.基于二维卷积提取HSI空间特征，融合高光谱图像光谱特征和空间特征的低维表示以及重构误差表示，联合密度估计网络进行端到端的优化，并利用分布式学习实现了大体积高光谱图像的异常检测.实验表明，所提出的E2E-SSCADE可以从光谱向量、空间维度以及重构空间三个角度更深层次地挖掘HSI固有信息的低维表示，构建更加准确的背景模型，在有效分离背景和异常目标的同时，结合分布式学习实现了快速、准确的大体积高光谱图像的异常检测，在6个经典HAD数据集上达到了99.07%的精度和3.41倍的检测速度.实验代码见

https：//github.com/majitao-xd/E2E-SSCADE.git

https://github.com/majitao-xd/E2E-SSCADE.git

Abstract

Hyperspectral image (HSI) is widely used in anomaly detection because of its rich spectral and spatial information

and plays an important role in the earth observation and deep space exploration. However

the existing hyperspectral anomaly detect

ion (HAD) methods based on density estimation have the following problems. First

there is no joint optimization of the two different objective functions of probability density estimation and feature representation

which results in the deep neural network being unable to learn more accurate probability density function and low-dimensional representation containing inherent information of HSI; the other is the lack of adaptive fusion of high-level spatial semantic information and low-dimensional epidemic spectral information. In addition

with the development of spectral imaging technology

the volume of HSI acquired by satellites or unmanned aerial vehicles is increasing. In the context of remote sensing big data

it becomes very difficult for traditional frameworks to process HSI

posing a great challenge to HAD. In this paper

based on the above problems

an end-to-end spectral-spatial cooperative autoencoding density estimation (E2E-SSCADE) model is proposed. The HSI spatial features are extracted based on two-dimensional convolution

and the spectral features and spatial features of hyperspectral images are combined with the low-dimensional representation and reconstruction error representation. The end-to-end optimization is carried out by combining the density estimation network

and the anomaly detection of large hyperspectral images is realized by distributed learning. Experiments show that the proposed E2E-SSCADE can excavate the low-dimensional representation of HSI intrinsic information from three perspectives of spectral vector

spatial dimension and reconstructed space

and construct a more accurate background model. With distributed training

fast and accurate anomaly detection of hyperspectral images is realized. The proposed method achieves 99.07% accuracy and 3.41 times faster detection on six classical HAD datasets.The code is available at

https://github.com/majitao-xd/E2E-SSCADE.git

关键词

Keywords

references

GHAMISI P , YOKOYA N , LI J , et al . Advances in hyperspectral image and signal processing: A comprehensive overview of the state of the art [J ] . IEEE Geoscience and Remote Sensing Magazine , 2017 , 5 ( 4 ): 37 - 78 .

LI S T , SONG W W , FANG L Y , et al . Deep learning for hyperspectral image classification: An overview [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 9 ): 6690 - 6709 .

GONG Z Q , ZHONG P , HU W D . Statistical loss and analysis for deep learning in hyperspectral image classification [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2021 , 32 ( 1 ): 322 - 333 .

JIA S , JIANG S G , LIN Z J , et al . A survey: Deep learning for hyperspectral image classification with few labeled samples [J ] . Neurocomputing , 2021 , 448 : 179 - 204 .

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 .

MATTEOLI S , VERACINI T , DIANI M , et al . A locally adaptive background density estimator: An evolution for RX-based anomaly detectors [J ] . IEEE Geoscience and Remote Sensing Letters , 2014 , 11 ( 1 ): 323 - 327 .

CARLOTTO M J . A cluster-based approach for detecting man-made objects and changes in imagery [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2005 , 43 ( 2 ): 374 - 387 .

LI W , DU Q . Collaborative representation for hyperspectral anomaly detection [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2015 , 53 ( 3 ): 1463 - 1474 .

XU Y , WU Z B , LI J , et al . Anomaly detection in hyperspectral images based on low-rank and sparse representation [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2016 , 54 ( 4 ): 1990 - 2000 .

ZHANG Y X , DU B , ZHANG L P , et al . A low-rank and sparse matrix decomposition-based mahalanobis distance method for hyperspectral anomaly detection [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2016 , 54 ( 3 ): 1376 - 1389 .

LI L , LI W , DU Q , et al . Low-rank and sparse decomposition with mixture of Gaussian for hyperspectral anomaly detection [J ] . IEEE Transactions on Cybernetics , 2021 , 51 ( 9 ): 4363 - 4372 .

LI W , WU G D , DU Q . Transferred deep learning for anomaly detection in hyperspectral imagery [J ] . IEEE Geoscience and Remote Sensing Letters , 2017 , 14 ( 5 ): 597 - 601 .

ZHANG L L , CHENG B Z . A stacked autoencoders-based adaptive subspace model for hyperspectral anomaly detection [J ] . Infrared Physics & Technology , 2019 , 96 : 52 - 60 .

JIANG T , LI Y S , XIE W Y , et al . Discriminative reconstruction constrained generative adversarial network for hyperspectral anomaly detection [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2020 , 58 ( 7 ): 4666 - 4679 .

CHALAPATHY R , CHAWLA S . Deep learning for anomaly detection: A survey [EB/OL ] . ( 2019-01-10 )[ 2022-05 ] . https://arxiv.org/abs/1901.03407 https://arxiv.org/abs/1901.03407 .

SONG S Z , ZHOU H X , YANG Y X , et al . Hyperspectral anomaly detection via convolutional neural network and low rank with density-based clustering [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2019 , 12 ( 9 ): 3637 - 3649 .

XIE W Y , LEI J , LIU B Z , et al . Spectral constraint adversarial autoencoders approach to feature representation in hyperspectral anomaly detection [J ] . Neural Networks , 2019 , 119 : 222 - 234 .

MAKHZANI A , SHLENS J , JAITLY N , et al . Adversarial autoencoders [EB/OL ] . ( 2015-11-18 )[ 2022-02 ] . https://arxiv.org/abs/1511.05644 https://arxiv.org/abs/1511.05644 .

XIE W Y , LIU B Z , LI Y S , et al . Spectral adversarial feature learning for anomaly detection in hyperspectral imagery [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2020 , 58 ( 4 ): 2352 - 2365 .

ZONG B , QI S , MIN M R , et al . Deep autoencoding Gaussian mixture model for unsupervised anomaly detection [C ] // 6th International Conference on Learning Representations . Vancouver : ICLR , 2018 : 1 - 19 .

JIANG K , XIE W Y , LEI J , et al . E2E-LIADE: End-to-end local invariant autoencoding density estimation model for anomaly target detection in hyperspectral image [J ] . IEEE Transactions on Cybernetics , 2022 , 52 ( 11 ): 11385 - 11396 .

HAUT J M , GALLARDO J A , PAOLETTI M E , et al . Cloud deep networks for hyperspectral image analysis [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 12 ): 9832 - 9848 .

SEDONA R , CAVALLARO G , RIEDEL M , et al . Enhancing large batch size training of deep models for remote sensing applications [C ] // 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS . Brussels : IEEE , 2021 : 1583 - 1586 .

HAUT J M , PAOLETTI M E , MORENO-ÁLVAREZ S , et al . Distributed deep learning for remote sensing data interpretation [J ] . Proceedings of the IEEE , 2021 , 109 ( 8 ): 1320 - 1349 .

HAUT J M , PAOLETTI M E . Cloud implementation of multinomial logistic regression for UAV hyperspectral images [J ] . IEEE Journal on Miniaturization for Air and Space Systems , 2020 , 1 ( 3 ): 163 - 171 .

ZHANG B , CHEN Z C , PENG D L , et al . Remotely sensed big data: Evolution in model development for information extraction [point of view] [J ] . Proceedings of the IEEE , 2019 , 107 ( 12 ): 2294 - 2301 .

WANG L Z , YAN J N , MA Y . Cloud Computing in Remote Sensing [M ] . Boca Raton : CRC Press , 2019 .

MA L , LIU Y , ZHANG X L , et al . Deep learning in remote sensing applications: A meta-analysis and review [J ] . ISPRS Journal of Photogrammetry and Remote Sensing , 2019 , 152 : 166 - 177 .

叶珍 , 白璘 , 何明一 . 高光谱图像空谱特征提取综述 [J ] . 中国图象图形学报 , 2021 , 26 ( 8 ): 1737 - 1763 .

YE Z , BAI L , HE M Y . Review of spatial-spectral feature extraction for hyperspectral image [J ] . Journal of Image and Graphics , 2021 , 26 ( 8 ): 1737 - 1763 . (in Chinese)

LI Y J , PARK J , ALIAN M , et al . A network-centric hardware/algorithm co-design to accelerate distributed training of deep neural networks [C ] // 2018 51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) . Fukuoka : IEEE , 2018 : 175 - 188 .

谢卫莹 , 马纪涛 , 蒋恺 , 等 . 基于空谱深度协同的高光谱异常检测方法 : CN114445720A [P ] . 2022-05-06 .

KANG X D , ZHANG X P , LI S T , et al . Hyperspectral anomaly detection with attribute and edge-preserving filters [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2017 , 55 ( 10 ): 5600 - 5611 .

SWETS J A , DAWES R M , MONAHAN J . Better decisions through science [J ] . Scientific American , 2000 , 283 ( 4 ): 82 - 87 .

BRADLEY P . The use of the area under the ROC curve in the evaluation of machine learning algorithms [J ] . Pattern Recognition , 1997 , 30 ( 7 ): 1145 - 1159 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据