高光谱遥感影像异常目标检测研究进展
Research progress on hyperspectral anomaly detection
- 2023年 页码：1-14
DOI： 10.11834/jrs.20232405
引用
扫 描 看 全 文
摘要
随着航空航天技术与遥感技术的不断发展，遥感影像在诸多领域的应用不断拓展，其中高光谱分辨率遥感影像具有“图谱合一”的特点，即该数据既包含了具有强大区分性的地物光谱信息，又包含了丰富的地物空间位置信息，因此高光谱数据具有非常大的应用潜力。高光谱异常目标检测问题，是在对目标先验信息未知的前提下，根据光谱与空间信息实现对区域中的异常目标的进行“盲”检测，因此其在资源调查、灾害救援等领域发挥了巨大的作用，是遥感领域非常重要的研究课题。本文针对高光谱遥感影像异常目标检测研究方向，首先总结阐述了目前高光谱异常目标检测问题的主要研究进展，根据算法原理的不同对现有主流算法进行了分类与总结，主要分成了基于统计学、基于数据表达、基于数据分解、基于深度学习等不同的种类的方法，并对每类方法的特点进行分析。随后通过对现有方法的调研、分析与总结，提出了数据库拓展、多源数据融合、算法实用化等高光谱异常检测研究未来发展的三个方向。
Abstract
With the continuous development of aerospace technology and remote sensing technology, the applications of remote sensing images in lots of fields have been expanding. Hyperspectral image (HSI) is a common type of remote sensing image which consists of a series of two-dimensional remote sensing images as a 3D data cube. Each two-dimensional image in HSI can reflect the reflection/radiation intensity of different wavelengths of electromagnetic waves, and each pixel of HSI corresponds to the spectral curve reflecting the spectral information in different wavelengths. Therefore, the hyperspectral remote sensing images have the feature of "map-spectrum integration", which contains not only the spectral information with strong discriminative, but also rich spatial information, so the hyperspectral data have great application potential.Hyperspectral anomaly detection is to detect the pixels in a scene with different characteristics from surrounding pixels and determines them as anomalous targets without the any prior knowledge of the target. Since hyperspectral anomaly detection is an unsupervised process that does not require any priori information about the target to be measured in advance, it plays a great role in real life. For example, anomaly target detection technology can be used to search and rescue people after a disaster, to quickly determine the fire point of a forest fire, and to search mineral point in mineral resource exploration. Hyperspectral anomaly detection has been a popular research direction in the area of remote sensing image processing in recent years and a large number of researchers have conducted extensive and in-depth research and achieved rich research results.However, hyperspectral anomaly detection still faces many difficult problems, such as the targets of the same material may exhibit different spectral characteristics due to the different imaging equipment and imaging environment, which may interfere with the detection results and lead to the problem of "same object with different spectrum", and the targets of different materials may also exhibit the problem of "different object with different spectrum". Then, most of the existing hyperspectral anomaly detection algorithms are only in the laboratory stage and with low technology maturity. Besides, the hyperspectral data may have lots of spectral bands that contains a large amount of redundant information, which makes the data processing difficult. Moreover, the number of publicly available hyperspectral anomaly detection datasets is insufficient and most of the datasets are very old.In this paper, we firstly summarize the main research progress of hyperspectral anomaly detection, and then classify and summarize the existing mainstream algorithms, mainly divided into five categories: statistics-based anomaly detection methods, data expression-based anomaly detection methods, data decomposition-based methods anomaly detection, deep learning-based methods anomaly detection and other methods. Besides, through the investigation, analysis and summary of the existing methods, three future development directions of hyperspectral anomaly detection are proposed, including database expansion: introduce newer dataset with more images and more sophisticated remote sensing sensors, multi-source data combination: take advantages of different imaging sensors and different types of remote sensing data; algorithm practical: enables the anomaly detection algorithms to be ported for application on real platforms.
关键词
遥感高光谱遥感高光谱异常检测深度学习矩阵分解
Keywords
remote sensinghyperspectral remote sensinghyperspectral anomaly detectiondeep learningmatrix factorization
references
Candès E J, Li X, Ma Y and Wright J. 2011. Robust principal component analysis? Journal of the ACM, 58(3): 1-37 [DOI: 10.1145/1970392.1970395http://dx.doi.org/10.1145/1970392.1970395]
Chen Y, Nasrabadi N M and Tran T D. 2011. Sparse representation for target detection in hyperspectral imagery. IEEE Journal of Selected Topics in Signal Processing, 5(3): 629-640 [DOI: 10.1109/JSTSP.2011.2113170http://dx.doi.org/10.1109/JSTSP.2011.2113170]
Cheng T and Wang B. 2019. Graph and total variation regularized low-rank representation for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 58(1): 391-406 [DOI: 10.1109/TGRS.2019.2936609http://dx.doi.org/10.1109/TGRS.2019.2936609]
Feng S, Tang S, Zhao C and Cui Y. 2021. A hyperspectral anomaly detection method based on low-rank and sparse decomposition with density peak guided collaborative representation. IEEE Transactions on Geoscience and Remote Sensing, 60: 1-13 [DOI: 10.1109/TGRS.2021.3054736http://dx.doi.org/10.1109/TGRS.2021.3054736]
Fu X, Jia S, Zhuang L, Zhuang L, Xu M, Zhou J and Li Q. 2021. Hyperspectral anomaly detection via deep plug-and-play denoising CNN regularization. IEEE Transactions on Geoscience and Remote Sensing, 59(11): 9553-9568 [DOI: 10.1109/TGRS.2021.3049224http://dx.doi.org/10.1109/TGRS.2021.3049224]
Geng X, Sun K, Ji L, and Zhao Y. 2014. A high-order statistical tensor based algorithm for anomaly detection in hyperspectral imagery. Scientific reports, 4(1): 1-7 [DOI: 10.1038/srep06869http://dx.doi.org/10.1038/srep06869]
Guo Q, Zhang B, Ran Q, Gao L, Li J and Plaza A. 2014. Weighted-RXD and linear filter-based RXD: Improving background statistics estimation for anomaly detection in hyperspectral imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2351-2366 [DOI: 10.1109/JSTARS.2014.2302446http://dx.doi.org/10.1109/JSTARS.2014.2302446]
Herwegab J A, Kerekesa J P, Weatherbeec O, Messingera D, Aardt J, Ientilucci E, Ninkov Z, Faulring J, Raqueno N and Meolad J. 2012. SpecTIR hyperspectral airborne Rochester experiment data collection campaign. [DOI: 10.1117/12.919268http://dx.doi.org/10.1117/12.919268]
Hu J, Zhang Y, Zhao M and Li P. 2022. Spatial-spectral extraction for hyperspectral anomaly detection. IEEE Geoscience and Remote Sensing Letters, 19: 1-5, [DOI: 10.1109/LGRS.2021.3130908].
Huyan N, Zhang X, Zhou H and Jiao L. 2018. 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 K, Xie W, Li Y, Lei J, He G and Du Q. 2020. Semisupervised spectral learning with generative adversarial network for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 58(7): 5224-5236 [DOI: 10.1109/TGRS.2020.2975295http://dx.doi.org/10.1109/TGRS.2020.2975295]
Jiang T, Xie W, Li Y and Du Q. 2020. Discriminative semi-supervised generative adversarial network for hyperspectral anomaly detection. IEEE International Geoscience and Remote Sensing Symposium, 2420-2423 [DOI: 10.1109/IGARSS39084.2020.9323688http://dx.doi.org/10.1109/IGARSS39084.2020.9323688]
Jiang T, Li Y, Xie W 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]
Kang X, Zhang X, Li S, Li K, Li J and Benediktsson J. 2017. Hyperspectral anomaly detection with attribute and edge-preserving filters. IEEE Transactions on Geoscience and Remote Sensing, 55(10): 5600-5611 [DOI: 10.1109/TGRS.2017.2710145http://dx.doi.org/10.1109/TGRS.2017.2710145]
Kwon H, Nasrabadi N M. 2005. Kernel RX-algorithm: A nonlinear anomaly detector for hyperspectral imagery. IEEE transactions on Geoscience and Remote Sensing, 43(2): 388-397 [DOI: 10.1109/TGRS.2004.841487http://dx.doi.org/10.1109/TGRS.2004.841487]
Li J, Zhang H, Zhang L and Ma L. 2015. Hyperspectral anomaly detection by the use of background joint sparse representation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2523-2533 [DOI: 10.1109/JSTARS.2015.2437073http://dx.doi.org/10.1109/JSTARS.2015.2437073]
Li K, Ling Q, Qin Y, Wang Y, Cai Y, Lin Z and An W. 2022. Spectral-spatial deep support vector data description for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, [DOI: 10.1109/TGRS.2022.3144192http://dx.doi.org/10.1109/TGRS.2022.3144192]
Li L, Li W, Du Q and Tao R. 2020. Low-rank and sparse decomposition with mixture of Gaussian for hyperspectral anomaly detection. IEEE Transactions on Cybernetics, 51(9): 4363-4372 [DOI: 10.1109/TCYB.2020.2968750http://dx.doi.org/10.1109/TCYB.2020.2968750]
Li Y, Jiang T, Xie W, Lei J and Du Q. 2021. Sparse coding-inspired GAN for hyperspectral anomaly detection in weakly supervised learning. IEEE Transactions on Geoscience and Remote Sensing, 60: 1-11 [DOI: 10.1109/TGRS.2021.3102048http://dx.doi.org/10.1109/TGRS.2021.3102048]
Li Z, Shi S, Wang L, Xu M and Li L. 2022. Unsupervised generative adversarial network with background enhancement and irredundant pooling for hyperspectral anomaly detection. remote sensing, 14(5): 1265 [DOI: 10.3390/rs14051265http://dx.doi.org/10.3390/rs14051265]
Li W and Du Q. 2014. 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]
Li W, Wu G and Du Q. 2017. Transferred deep learning for anomaly detection in hyperspectral imagery. IEEE Geoscience and Remote Sensing Letters, 14(5): 597-601 [DOI: 10.1109/LGRS.2017.2657818http://dx.doi.org/10.1109/LGRS.2017.2657818]
Li Z, Zhang Y and Zhang J. 2021. Hyperspectral anomaly Detection for spectral anomaly targets via spatial and spectral constraints. IEEE Transactions on Geoscience and Remote Sensing, 2021 [DOI: 10.1109/TGRS.2021.3091156http://dx.doi.org/10.1109/TGRS.2021.3091156]
Ling Q, Guo Y, Lin Z and An W. 2018. A constrained sparse representation model for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 57(4): 2358-2371 [DOI: 10.1109/TGRS.2018.2872900http://dx.doi.org/10.1109/TGRS.2018.2872900]
Liu G, Lin Z, Yan S, Sun J, Yu Y and Ma Y. 2012. 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]
Liu W, Wu X, Qu H and Wang F. 2018. Improved hyperspectral image anomaly detection algorithm with cooperative representation. Application Research of Computers， 35(12): 310-313
刘万军, 武小杰, 曲海成, 王凤. 2018. 改进协同表示的高光谱图像异常检测算法. 计算机应用研究，35(12): 310-313 [DOI: 10.3969/j.issn.1001-3695.2018.12.068http://dx.doi.org/10.3969/j.issn.1001-3695.2018.12.068]
Ma D, Yuan Y and Wang Q. 2017. A sparse dictionary learning method for hyperspectral anomaly detection with capped norm. IEEE International Geoscience and Remote Sensing Symposium, 648-651 [DOI: 10.1109/IGARSS.2017.8127037http://dx.doi.org/10.1109/IGARSS.2017.8127037]
Ma X, Zhang X, Huyan N, Tang X and Jiao L. 2021. Background representation learning with structural constraint for hyperspectral anomaly detection. IEEE Geoscience and Remote Sensing Letters, 19: 1-5 [DOI: 10.1109/LGRS.2021.3073176http://dx.doi.org/10.1109/LGRS.2021.3073176]
Matteoli S, Veracini T, Diani M and Corsini G. 2013. A locally adaptive background density estimator: An evolution for RX-based anomaly detectors. IEEE geoscience and remote sensing letters, 11(1): 323-327 [DOI: 10.1109/LGRS.2013.2257670http://dx.doi.org/10.1109/LGRS.2013.2257670]
Qu Y, Wang W, Guo R, Ayhan B, Kwan C, Vance S and Qi H. 2018. Hyperspectral anomaly detection through spectral unmixing and dictionary-based low-rank decomposition. IEEE Transactions on Geoscience and Remote Sensing, 56(8): 4391-4405 [DOI: 10.1109/TGRS.2018.2818159http://dx.doi.org/10.1109/TGRS.2018.2818159]
Reed I S and Yu X. 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]
Song S, Zhou H, Yang Y and Song J. 2019. Hyperspectral anomaly detection via convolutional neural network and low rank with density-based clustering. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(9): 3637-3649 [DOI: 10.1109/JSTARS.2019.2926130http://dx.doi.org/10.1109/JSTARS.2019.2926130]
Su H, Wu Z, Zhu A X and Du Q. 2020. Low rank and collaborative representation for hyperspectral anomaly detection via robust dictionary construction. ISPRS Journal of Photogrammetry and Remote Sensing, 169: 195-211 [DOI: 10.1016/j.isprsjprs.2020.09.008http://dx.doi.org/10.1016/j.isprsjprs.2020.09.008]
Sun W, Liu C, Li J, Lai Y and Li W. 2014. Low-rank and sparse matrix decomposition-based anomaly detection for hyperspectral imagery. Journal of Applied Remote Sensing, 8(1): 083641 [DOI: 10.1117/1.JRS.8.083641http://dx.doi.org/10.1117/1.JRS.8.083641]
Taghipour A and Ghassemian H. 2019. Unsupervised hyperspectral target detection using spectral residual of deep autoencoder networks. 4th International Conference on Pattern Recognition and Image Analysis, 52-57 [DOI: 10.1109/PRIA.2019.8785982http://dx.doi.org/10.1109/PRIA.2019.8785982]
Taghipour A and Ghassemian H. 2021. A bottom-up and top-down human visual attention approach for hyperspectral anomaly detection. Journal of Visual Communication and Image Representation, 77: 103113 [DOI: 10.1016/j.jvcir.2021.103113http://dx.doi.org/10.1016/j.jvcir.2021.103113]
Tao R, Zhao X, Li W, Li H and Du Q. 2019. Hyperspectral anomaly detection by fractional Fourier entropy. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(12): 4920-4929 [DOI: 10.1109/JSTARS.2019.2940278http://dx.doi.org/10.1109/JSTARS.2019.2940278]
Tu B, Yang X, Li N, Zhou C and He D. 2020. Hyperspectral anomaly detection via density peak clustering. Pattern Recognition Letters, 129: 144-149 [DOI: 10.1016/j.patrec.2019.11.022http://dx.doi.org/10.1016/j.patrec.2019.11.022]
Tu B, Yang X, Zhou C, He D and Plaza A. 2020. Hyperspectral anomaly detection using dual window density. IEEE Transactions on Geoscience and Remote Sensing, 58(12): 8503-8517 [DOI: 10.1109/TGRS.2020.2988385http://dx.doi.org/10.1109/TGRS.2020.2988385]
Vafadar M and Ghassemian H. 2018. Anomaly detection of hyperspectral imagery using modified collaborative representation. IEEE Geoscience and Remote Sensing Letters, 15(4): 577-581 [DOI: 10.1109/LGRS.2018.2796083http://dx.doi.org/10.1109/LGRS.2018.2796083]
Wang Y, Wang F, Zhu Q, Song M and Yu C. 2021. Transferred tensor decomposition-based deep learning for hyperspectral anomaly detection. IEEE International Geoscience and Remote Sensing Symposium, 5279-5282 [DOI: 10.1109/IGARSS47720.2021.9555078http://dx.doi.org/10.1109/IGARSS47720.2021.9555078]
Xiang P, Song J, Qin H, Tan W, Li H and Zhou H. 2021. Visual attention and background subtraction with adaptive weight for hyperspectral anomaly detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 2270-2283 [DOI: 10.1109/JSTARS.2021.3052968http://dx.doi.org/10.1109/JSTARS.2021.3052968]
Xie W, Jiang T, Li Y, Jia X and Lei J. 2019. Structure tensor and guided filtering-based algorithm for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 57(7): 4218-4230 [DOI: 10.1109/TGRS.2018.2890212http://dx.doi.org/10.1109/TGRS.2018.2890212]
Xie W, Liu B, Li Y, Lie J and Du Q. 2020. Autoencoder and adversarial-learning-based semisupervised background estimation for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 58(8): 5416-5427 [DOI: 10.1109/TGRS.2020.2965995http://dx.doi.org/10.1109/TGRS.2020.2965995]
Xu Y, Wu Z, Li J, Plaza A and Wei Z. 2015. 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]
Yuan Y, Wang Q and Zhu G. 2014. Fast hyperspectral anomaly detection via high-order 2-D crossing filter. IEEE Transactions on Geoscience and Remote Sensing, 53(2): 620-630 [DOI: 10.1109/TGRS.2014.2326654http://dx.doi.org/10.1109/TGRS.2014.2326654]
Zhang L and Zhao C. 2017. Hyperspectral anomaly detection based on spectral–spatial background joint sparse representation. European Journal of Remote Sensing, 50(1): 362-376 [DOI: 10.1080/22797254.2017.1331697http://dx.doi.org/10.1080/22797254.2017.1331697]
Zhang L and Cheng B. 2021. Fractional Fourier transform and transferred CNN based on tensor for hyperspectral anomaly detection. IEEE Geoscience and Remote Sensing Letters, 19: 1-5 [DOI: 10.1109/LGRS.2021.3072249http://dx.doi.org/10.1109/LGRS.2021.3072249]
Zhang L, Cheng B, Tan S and Wang Y. 2022. Fractional Fourier transform based joint adaptive subspace detection for hyperspectral anomaly detection. IEEE Geoscience and Remote Sensing Letters, 19: 1-5 [DOI: 10.1109/LGRS.2022.3150929http://dx.doi.org/10.1109/LGRS.2022.3150929]
Zhang L, Ma J, Cheng B and Lin F. 2022. Fractional Fourier transform-based tensor RX for hyperspectral anomaly detection. Remote Sensing, 14(3): 797 [DOI: 10.3390/rs14030797http://dx.doi.org/10.3390/rs14030797]
Zhang X, Wen G and Dai W. 2016. A tensor decomposition-based anomaly detection algorithm for hyperspectral image. IEEE Transactions on Geoscience and Remote Sensing, 54(10): 5801-5820 [DOI: 10.1109/TGRS.2016.2572400http://dx.doi.org/10.1109/TGRS.2016.2572400]
Zhang Y, Du B, Zhang L and Wang S. 2015. A low-rank and sparse matrix decomposition-based Mahalanobis distance method for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 54(3): 1376-1389 [DOI: 10.1109/TGRS.2015.2479299http://dx.doi.org/10.1109/TGRS.2015.2479299]
Zhao C, Li C, Feng S and Jia X. 2022. Enhanced total variation regularized representation model with endmember background dictionary for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 1-12 [DOI: 10.1109/TGRS.2021.3128183http://dx.doi.org/10.1109/TGRS.2021.3128183]
Zhao R, Du B and Zhang L. 2017. Hyperspectral anomaly detection via a sparsity score estimation framework. IEEE Transactions on Geoscience and Remote Sensing, 55(6): 3208-3222 [DOI: 10.1109/TGRS.2017.2664658http://dx.doi.org/10.1109/TGRS.2017.2664658]
Zhou J, Kwan C, Ayhan B and Eismann M. 2016. A novel cluster kernel RX algorithm for anomaly and change detection using hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(11): 6497-6504 [DOI: 10.1109/TGRS.2016.2585495http://dx.doi.org/10.1109/TGRS.2016.2585495]
Zhou T and Tao D. 2011. Godec: Randomized low-rank & sparse matrix decomposition in noisy case. Proceedings of the 28th International Conference on Machine Learning, 33-40
Zhu L, Wen G, Qiu S and Zhang X. 2019. A hybrid statistics and representation-based anomaly detector for hyperspectral images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(9): 3650-3664 [DOI: 10.1109/JSTARS.2019.2930147http://dx.doi.org/10.1109/JSTARS.2019.2930147]
Zhuang L, Ye. Z and Junping. Z. 2022. Hyperspectral anomaly detection for spectral anomaly targets via spatial and spectral constraints. IEEE Transactions on Geoscience and Remote Sensing, 60:.1-15 [DOI: 10.1109/TGRS.2021.3091156http://dx.doi.org/10.1109/TGRS.2021.3091156]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
信息工程大学 地理空间信息学院
北京遥感信息研究所
中国矿业大学 环境与测绘学院
中国矿业大学 人工智能研究院
中国科学院空天信息创新研究院
- 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