深度展开网络的高光谱异常探测
Deep unfolding network for hyperspectral anomaly detection
- 2024年28卷第1期 页码：69-77
纸质出版日期： 2024-01-07
DOI： 10.11834/jrs.20233075
移动端阅览
浏览全部资源
扫码关注微信
摘要
在现有基于物理模型的高光谱异常探测HAD（Hyperspectral Anomaly Detection）方法中，低秩表示LRR（Low-Rank Representation）模型以其强大的背景和目标特征分离能力而受到广泛的关注和采用。然而，由于依赖手动参数的选择以及较差的泛化性，导致其实际应用受到限制。为此，本文将LRR模型与深度学习技术相结合，提出了一种新的适用于HAD的基础深度展开网络，称为LRR-Net。该方法借助交替方向乘法ADMM（Alternating Direction Method of Multipliers）优化器高效地求解LRR模型，并将其求解步骤耦合至深度网络中以指导其搜索过程，为深度网络提供了一定的理论基础，具有较强的可解释性。此外，LRR-Net以端到端的方式将一系列正则化的参数转换为可学习的网络参数，从而避免了手动调参。4组不同的高光谱异常探测实验证明了LRR-Net的有效性，与其他无监督的异常探测方法相比，LRR-Net具有较强的泛化性和鲁棒性，能够提高HAD的精度。
Abstract
Hyperspectral Anomaly Detection(HAD) is one of the most critical topic in hyperspectral remote sensing and has been extensively addressed in the literature over the past decade. Among them
Low-Rank Representation(LRR) models are widely used owing to their powerful separation ability for the background and targets. But their applications in practical situations still remain limited due to the extreme dependence on manual parameter selection and relatively poor generalization ability. To this end
this paper combines the LRR model with deep learning techniques to propose a new underlying network for HAD
called LRR-Net. This method efficiently solves the LRR model with the help of the Alternating Direction Method of Multipliers (ADMM) optimizer
and incorporates the solution as a priori knowledge into the deep network to guide the optimization of parameters
providing a theoretical basis for deep networks. In addition
LRR-Net converts a series of regularized parameters into learnable network parameters in an end-to-end manner
thus avoiding manual tuning of parameters. Experimental results obtained from publicly available datasets and our datasets demonstrate that the LRR-Net method outperforms many state-of-the-art model-based and deep-based algorithms of hyperspectral anomaly detection. Overall
deep learning networks are powerful in learning and are robust compared to traditional models in processing datasets with different complexity. However
despite the strong fitting ability of deep learning data
the necessary prior information is lacking
which often makes the algorithm fall into the local optima
which leads to the failure of deep learning to guarantee the stability of HAD results. The model-based algorithm can better make up for this defect
which can often get better results by improving the separability between the background and the target. Nonetheless
these LRR-based methods are unable to effectively suppress background noise due to their limited representation power
such as shadows
trees
and edges in complex scenes
with relatively large volatility in detection effects. The LRR-Net presented in this paper combines the advantages of the above two methods
and the experimental results of four typical scenarios show that the search of the optimal parameters in the neural network can effectively solve the HAD problem in an adaptive way
which is more physically meaningful.
关键词
高光谱遥感影像异常探测深度展开低秩表示（LRR）交替方向乘子法（ADMM）
Keywords
hyperspectral remote sensing imageanomaly detectiondeep unfoldingLow-Rank Representation (LRR)Alternating Direction Multiplier Method (ADMM)
references
Boyd S, Parikh N, Chu E, Peleato B and Eckstein J. 2011. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends® in Machine Learning, 3(1): 1-122 [DOI: 10.1561/2200000016http://dx.doi.org/10.1561/2200000016]
Chang C I. 2022. Effective anomaly space for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5526624 [DOI: 10.1109/TGRS.2022.3161632http://dx.doi.org/10.1109/TGRS.2022.3161632]
Chen S Y, Yang S M, Kalpakis K and Chang C I. 2013. Low-rank decomposition-based anomaly detection//Processing of SPIE 8743, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX. Baltimore: SPIE: 87430N [DOI: 10.1117/12.2015652http://dx.doi.org/10.1117/12.2015652]
Goodfellow I, Bengio Y and Courville A. 2016. Deep Learning. Cambridge: MIT Press
Hong D F, Zhang B, Li H, Li Y X, Yao J, Li C, Werner M., Chanussot J., Zipf A., Xiao X X. Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks. Remote Sensing of Environment, 299(15)：0034-4257 [DOI: 10.1016/j.rse.2023.113856http://dx.doi.org/10.1016/j.rse.2023.113856]
Hong D F, Zhang B, Li X, Li Y, Li C, Yao J, Yokoya N, Li H, Jia X, Plaza A, Gamba P, Benediktsson J, Chanusso J. “SpectralGPT: Spectral Foundation Model.” arXiv preprint arXiv:2311.07113, 2023.
Huyan N, Zhang X R, Zhou H Y and Jiao L C. 2019. Hyperspectral anomaly detection via background and potential anomaly dictionaries construction. IEEE Transactions on Geoscience and Remote Sensing, 57(4): 2263-2276 [DOI: 10.1109/TGRS.2018.2872590http://dx.doi.org/10.1109/TGRS.2018.2872590]
Jiang T, Li Y S, Xie W Y and Du Q. 2020. Discriminative reconstruction constrained generative adversarial network for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 58(7): 4666-4679 [DOI: 10.1109/TGRS.2020.2965961http://dx.doi.org/10.1109/TGRS.2020.2965961]
Khazai S, Homayouni S, Safari A and Mojaradi B. 2011. Anomaly detection in hyperspectral images based on an adaptive support vector method. IEEE Geoscience and Remote Sensing Letters, 8(4): 646-650 [DOI: 10.1109/LGRS.2010.2098842http://dx.doi.org/10.1109/LGRS.2010.2098842]
Li W and Du Q. 2015. Collaborative representation for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 53(3): 1463-1474 [DOI: 10.1109/TGRS.2014.2343955http://dx.doi.org/10.1109/TGRS.2014.2343955]
Lin Z C, Liu R S and Su Z X. 2011. Linearized alternating direction method with adaptive penalty for low-rank representation//Proceedings of the 24th International Conference on Neural Information Processing Systems (NIPS). Granada: Curran Associates Inc.: 612-620
Liu G C, Lin Z C, Yan S C, Sun J, Yu Y and Ma Y. 2013. Robust recovery of subspace structures by low-rank representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1): 171-184 [DOI: 10.1109/TPAMI.2012.88http://dx.doi.org/10.1109/TPAMI.2012.88]
Manolakis D and Shaw G. 2002. Detection algorithms for hyperspectral imaging applications. IEEE Signal Processing Magazine, 19(1): 29-43 [DOI: 10.1109/79.974724http://dx.doi.org/10.1109/79.974724]
Molero J M, Garzon E M, Garcia I and Plaza A. 2013. Analysis and optimizations of global and local versions of the RX algorithm for anomaly detection in hyperspectral data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2): 801-814 [DOI: 10.1109/JSTARS.2013.2238609http://dx.doi.org/10.1109/JSTARS.2013.2238609]
Reed I S and Yu X L. 1990. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution. IEEE Transactions on Acoustics, Speech, and Signal Processing, 38(10): 1760-1770 [DOI: 10.1109/29.60107http://dx.doi.org/10.1109/29.60107]
Shen H F, Jiang M H, Li J, Zhou C X, Yuan Q Q and Zhang L P. 2022. Coupling model- and data-driven methods for remote sensing image restoration and fusion: improving physical interpretability. IEEE Geoscience and Remote Sensing Magazine, 10(2): 231-249 [DOI: 10.1109/MGRS.2021.3135954http://dx.doi.org/10.1109/MGRS.2021.3135954]
Tong Q X, Zhang B and Zhang L F. 2016. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 20(5): 689-707
童庆禧, 张兵, 张立福. 2016. 中国高光谱遥感的前沿进展. 遥感学报, 20(5): 689-707 [DOI: 10.11834/jrs.20166264http://dx.doi.org/10.11834/jrs.20166264]
Vane G and Goetz A F H. 1988. Terrestrial imaging spectroscopy. Remote Sensing of Environment, 24(1): 1-29 [DOI: 10.1016/0034-4257(88)90003-Xhttp://dx.doi.org/10.1016/0034-4257(88)90003-X]
Wang S Y, Wang X Y, Zhang L P and Zhong Y F. 2022. Auto-AD: autonomous hyperspectral anomaly detection network based on fully convolutional autoencoder. IEEE Transactions on Geoscience and Remote Sensing, 60: 5503314 [DOI: 10.1109/TGRS.2021.3057721http://dx.doi.org/10.1109/TGRS.2021.3057721]
Wu X, Hong D F and Chanussot J. 2023. UIU-Net: U-Net in U-Net for infrared small object detection. IEEE Transactions on Image Processing, 32: 364-376 [DOI: 10.1109/TIP.2022.3228497http://dx.doi.org/10.1109/TIP.2022.3228497]
Xie Q, Zhou M H, Zhao Q, Meng D Y, Zuo W M and Xu Z B. 2019. Multispectral and hyperspectral image fusion by MS/HS fusion net//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach: IEEE: 1585-1515 [DOI: 10.1109/CVPR.2019.00168http://dx.doi.org/10.1109/CVPR.2019.00168]
Xiong F C, Zhou J, Tao S Y, Lu J F and Qian Y T. 2022a. SNMF-Net: learning a deep alternating neural network for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 60: 5510816 [DOI: 10.1109/TGRS.2021.3081177http://dx.doi.org/10.1109/TGRS.2021.3081177]
Xiong F C, Zhou J, Tao S Y, Lu J F, Zhou J T and Qian Y T. 2022b. SMDS-Net: model guided spectral-spatial network for hyperspectral image denoising. IEEE Transactions on Image Processing, 31: 5469-5483 [DOI: 10.1109/TIP.2022.3196826http://dx.doi.org/10.1109/TIP.2022.3196826]
Xu Y, Wu Z B, Li J, Plaza A and Wei Z H. 2016. Anomaly detection in hyperspectral images based on low-rank and sparse representation. IEEE Transactions on Geoscience and Remote Sensing, 54(4): 1990-2000 [DOI: 10.1109/TGRS.2015.2493201http://dx.doi.org/10.1109/TGRS.2015.2493201]
Yang L L, Li C, Han J G, Chen C, Ye Q X, Zhang B C, Cao X B and Liu W Q. 2017. Image reconstruction via manifold constrained convolutional sparse coding for image sets. IEEE Journal of Selected Topics in Signal Processing, 11(7): 1072-1081 [DOI: 10.1109/JSTSP.2017.2743683http://dx.doi.org/10.1109/JSTSP.2017.2743683]
Yang Y, Sun J, Li H B and Xu Z B. 2020. ADMM-CSNet: a deep learning approach for image compressive sensing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(3): 521-538 [DOI: 10.1109/TPAMI.2018.2883941http://dx.doi.org/10.1109/TPAMI.2018.2883941]
Zhang B. 2016. Advancement of hyperspectral image processing and information extraction. Journal of Remote Sensing, 20(5): 1062-1090
张兵. 2016. 高光谱图像处理与信息提取前沿. 遥感学报, 20(5): 1062-1090 [DOI: 10.11834/jrs.20166179http://dx.doi.org/10.11834/jrs.20166179]
Zhang B. 2018. Remotely sensed big data era and intelligent information extraction. Geomatics and Information Science of Wuhan University, 43(12): 1861-1871
张兵. 2018. 遥感大数据时代与智能信息提取. 武汉大学学报(信息科学版), 43(12): 1861-1871 [DOI: 10.13203/j.whugis20180172http://dx.doi.org/10.13203/j.whugis20180172]
Zhang Y, Hua W S, Yan Y, Cui Z H and Suo W K. 2019. Progress in hyperspectral anomaly target detection. Laser Journal, 40(7): 6-9
张炎, 华文深, 严阳, 崔子浩, 索文凯. 2019. 高光谱异常目标检测算法研究进展. 激光杂志, 40(7): 6-9 [DOI: 10.14016/j.cnki.jgzz.2019.07.006http://dx.doi.org/10.14016/j.cnki.jgzz.2019.07.006]
Zhu D H, Du B and Zhang L P. 2020. Band selection-based collaborative representation for anomaly detection in hyperspectral images. Journal of Remote Sensing, 24(4): 427-438
朱德辉, 杜博, 张良培. 2020. 波段选择协同表达高光谱异常探测算法. 遥感学报, 24(4): 427-438 [DOI: 10.11834/jrs.20209187http://dx.doi.org/10.11834/jrs.20209187]
文章被引用时，请邮件提醒。
提交
相关作者
杜博 武汉大学 计算机学院
张良培 武汉大学 测绘遥感信息工程国家重点实验室
朱德辉 武汉大学 测绘遥感信息工程国家重点实验室
杨刚 宁波大学 地理与空间信息技术系
张殿发 宁波大学 地理与空间信息技术系
李飞 宁波大学 地理与空间信息技术系
孙伟伟 宁波大学 地理与空间信息技术系
岑奕 中国科学院遥感与数字地球研究所
相关机构
武汉大学 测绘遥感信息工程国家重点实验室
武汉大学 计算机学院
宁波大学 地理与空间信息技术系
武汉大学 测绘遥感信息工程国家重点实验室
中国科学院遥感与数字地球研究所
选择翻译语言
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部