浏览全部资源
扫码关注微信
Published： 07 January 2024 ，
扫 描 看 全 文
贾森，刘宽，徐萌，朱家松.2024.基于空谱多路自编码器的高光谱图像异常检测.遥感学报，28（1）： 55-68
Jia S，Liu K，Xu M and Zhu J S. 2024. Hyperspectral anomaly detection based on spatial-spectral multichannel autoencoders. National Remote Sensing Bulletin， 28（1）：55-68
高光谱图像异常检测作为一种无监督的目标检测，主要存在异常目标类型多样化、异常与背景不易区分、以及检测精度受场景影响大等难题。针对以上问题，本文提出了一种基于空谱多路自编码器的高光谱图像异常检测方法。首先，提出一种加权空谱Gabor滤波方法，提取高光谱图像的多尺度空谱特征；其次，采用多路自编码器降低多尺度空谱特征在光谱维的冗余度，提取空谱特征中的主要信息；最后，利用得到的主要空谱特征，结合形态学滤波与双曲正切函数进行特征增强，以提高异常与背景噪声的区分度。本文提出的方法是一种即插即用的异常检测方法，无需额外的参数输入；多路自编码器提取了多尺度主要空谱特征，以应对异常目标类型多样化的难题；通过特征增强提高了背景与异常的区分度。将本文提出的方法与9种流行的异常检测方法相比，在5个高光谱数据集上进行验证，通过对比异常检测结果图、接收机操作特性（Receiver Operating Characteristic，ROC）曲线、ROC曲线下覆盖的面积AUC（Area Under Curve）以及异常像元与背景像元的箱型图等评价指标，证明了本文方法优于其他9种方法。
Hyperspectral anomaly detection is a type of unsupervised target detection that is crucial in the national economy and attracts the attention of numerous researchers. However
hyperspectral anomaly detection faces several challenges
such as diversified anomaly targets
difficulty in distinguishing anomalies from the background
and low detection accuracy. A hyperspectral anomaly detection method based on multichannel autoencoders is proposed to form a high-dimensional spatial-spectral feature space to address the above challenges. First
weighted spatial-spectral Gabor kernels with different scales and directions are proposed to extract the spatial-spectral features from hyperspectral images. These Gabor kernels are then redefined to increase the gap between the central and surrounding values in the kernels. The spatial-spectral features are extracted by weighted spatial-spectral Gabor kernels to form a high-dimensional spatial-spectral feature space. Second
multichannel autoencoders reduce the redundancy of multiscale spatial-spectral features in spectral dimension
extract the principal features from high-dimensional spatial-spectral feature space
and transform them into the principal feature representation space. Finally
a feature enhancement method based on hyperbolic tangent function and morphological filters is proposed to improve the distinction between abnormal targets and background noise and address the background noise in the spatial dimension. Mahalanobis distance is used to detect anomalies in the enhanced principal feature representation space. The proposed method is compared with nine state-of-the-art anomaly detection methods on five hyperspectral data sets. Anomaly Detection Maps (ADMs)
Receiver Operating Characteristics (ROCs)
Area Under Curves (AUCs)
and box plots between abnormal and background pixels are used to evaluate the performance of the compared methods. AUC is a quantitative evaluation method
and the others are qualitative evaluation methods. The anomaly detection maps obtained by the proposed method easily locates abnormal targets compared with other methods. The ROC curves on five hyperspectral data sets show that the proposed method has a superior performance. The AUC values of five hyperspectral data sets are 0.9910
0.9912
0.9968
0.9806
and 0.9812. The box plots show that the proposed method increases the gap between the anomalies and the background. The ablation experiments show that weighted spatial-spectral Gabor can extract more significant spatial-spectral features than three-dimensional Gabor. The principal feature representation space obtained by multichannel autoencoders is highly conducive to hyperspectral anomaly detection and improves detection accuracy. The feature enhancement method based on hyperbolic tangent function can improve the distinction between abnormal targets and background noise. The proposed method can extract significant spatial-spectral features from hyperspectral images to address the diversification of anomaly types and form a high-dimensional spatial-spectral feature space. The multichannel autoencoders convert the high-dimensional spatial-spectral feature space into the principal feature representation space
which can effectively reduce band redundancy in the spectral dimension and decrease the computational complexity in the anomaly detection process. The feature enhancement method based on hyperbolic tangent function can significantly improve the distinction between anomalies and background noise to locate the abnormal target.
高光谱图像异常检测多路自编码器加权空谱Gabor双曲正切函数特征增强
hyperspectral imageanomaly detectionmultichannel autoencodersweighted spatial-spectral Gaborhyperbolic tangent functionfeature enhancement method
Chang C I. 2000. An information-theoretic approach to spectral variability, similarity, and discrimination for hyperspectral image analysis. IEEE Transactions on Information Theory, 46(5): 1927-1932 [DOI: 10.1109/18.857802http://dx.doi.org/10.1109/18.857802]
Chang S Z, Du B and Zhang L P. 2019. A sparse autoencoder based hyperspectral anomaly detection algorihtm using residual of reconstruction error//IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium. Yokohama: IEEE: 5488-5491 [DOI: 10.1109/IGARSS.2019.8898697http://dx.doi.org/10.1109/IGARSS.2019.8898697]
Chen S Y, Yang S M, Kalpakis K and Chang C I. 2013. Low-rank decomposition-based anomaly detection//Proceedings Volume 8743, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX. Baltimore: SPIE: 171-177 [DOI: 10.1117/12.2015652http://dx.doi.org/10.1117/12.2015652]
Cheng B Z, Zhao C H and Zhang L L. 2021. Research advances of anomaly target detection algorithms for hyperspectral imagery. Electronics Optics and Control, 28(5): 56-59, 65
成宝芝, 赵春晖, 张丽丽. 2021. 高光谱图像异常目标检测算法研究进展. 电光与控制, 28(5): 56-59, 65 [DOI: 10.3969/j.issn.1671-637X.2021.05.013http://dx.doi.org/10.3969/j.issn.1671-637X.2021.05.013]
Fan G H, Ma Y, Mei X G, Fan F, Huang J and Ma J Y. 2022. Hyperspectral anomaly detection with robust graph autoencoders. IEEE Transactions on Geoscience and Remote Sensing, 60: 5511314 [DOI: 10.1109/TGRS.2021.3097097http://dx.doi.org/10.1109/TGRS.2021.3097097]
Han Z, Gao L R, Zhang B, Sun X and Li Q T. 2020. Nonlinear hyperspectral unmixing algorithm based on deep autoencoder networks. Journal of Remote Sensing, 24(4): 388-400
韩竹, 高连如, 张兵, 孙旭, 李庆亭. 2020. 高分五号高光谱图像自编码网络非线性解混. 遥感学报, 24(4): 388-400 [DOI: 10.11834/jrs.20209188http://dx.doi.org/10.11834/jrs.20209188]
Imani M. 2018. Anomaly detection using morphology-based collaborative representation in hyperspectral imagery. European Journal of Remote Sensing, 51(1): 457-471 [DOI: 10.1080/22797254.2018.1446727http://dx.doi.org/10.1080/22797254.2018.1446727]
Jia S, Liao J H, Xu M, Li Y, Zhu J S, Sun W W, Jia X P and Li Q Q. 2022. 3-D Gabor convolutional neural network for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60: 5509216 [DOI: 10.1109/TGRS.2021.3087186http://dx.doi.org/10.1109/TGRS.2021.3087186]
Kang X D, Zhang X P, Li S T, Li K L, Li J and Benediktsson J A. 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]
Kingma D P and Welling M. 2019. An introduction to variational autoencoders. Foundations and Trends® in Machine Learning, 12(4): 307-392 [DOI: 10.1561/2200000056http://dx.doi.org/10.1561/2200000056]
Li S T, Zhang K Z, Duan P H and Kang X D. 2020. Hyperspectral anomaly detection with kernel isolation forest. IEEE Transactions on Geoscience and Remote Sensing, 58(1): 319-329 [DOI: 10.1109/TGRS.2019.2936308http://dx.doi.org/10.1109/TGRS.2019.2936308]
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]
Liu C Y, Li J, He L, Plaza A, Li S T and Li B. 2021. Naive Gabor networks for hyperspectral image classification. IEEE Transactions on Neural Networks and Learning Systems, 32(1): 376-390 [DOI: 10.1109/TNNLS.2020.2978760http://dx.doi.org/10.1109/TNNLS.2020.2978760]
Ma Y, Fan G H, Jin Q W, Huang J, Mei X G and Ma J Y. 2021. Hyperspectral anomaly detection via integration of feature extraction and background purification. IEEE Geoscience and Remote Sensing Letters, 18(8): 1436-1440 [DOI: 10.1109/LGRS.2020.2998809http://dx.doi.org/10.1109/LGRS.2020.2998809]
Molero J M, Garzón E M, García 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]
Pagare M S and Risodkar Y R. 2018. Low-rank and sparse representation for anomaly detection in hyperspectral images//2018 International Conference on Advances in Communication and Computing Technology (ICACCT). Sangamner: IEEE: 594-597 [DOI: 10.1109/ICACCT.2018.8529636http://dx.doi.org/10.1109/ICACCT.2018.8529636]
Rasti B, Hong D F, Hang R L, Ghamisi P, Kang X D, Chanussot J and Benediktsson J A. 2020. Feature extraction for hyperspectral imagery: the evolution from shallow to deep: overview and toolbox. IEEE Geoscience and Remote Sensing Magazine, 8(4): 60-88 [DOI: 10.1109/MGRS.2020.2979764http://dx.doi.org/10.1109/MGRS.2020.2979764]
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]
Ren L, Zhao L Y and Wang Y L. 2020. A superpixel-based dual window RX for hyperspectral anomaly detection. IEEE Geoscience and Remote Sensing Letters, 17(7): 1233-1237 [DOI: 10.1109/LGRS.2019.2942949http://dx.doi.org/10.1109/LGRS.2019.2942949]
Sun W W, Liu C, Li J L, Lai Y M and Li W Y. 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]
Sun W W, Yang G, Li J L and Zhang D F. 2018. Randomized subspace-based robust principal component analysis for hyperspectral anomaly detection. Journal of Applied Remote Sensing, 12(1): 015015 [DOI: 10.1117/1.JRS.12.015015http://dx.doi.org/10.1117/1.JRS.12.015015]
Tao R, Zhao X D, Li W, Li H C 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]
Vanegas F, Bratanov D, Powell K, Weiss J and Gonzalez F. 2018. A novel methodology for improving plant pest surveillance in vineyards and crops using UAV-based hyperspectral and spatial data. Sensors, 18(1): 260 [DOI: 10.3390/s18010260http://dx.doi.org/10.3390/s18010260]
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]
Yuan J W, Wu C, Du B, Zhang L P and Wang S G. 2020. Analysis of landscape pattern on urban land use based on GF-5 hyperspectral data. Journal of Remote Sensing, 24(4): 465-478
袁静文, 武辰, 杜博, 张良培, 王树根. 2020. 高分五号高光谱遥感影像的城市土地利用景观格局分析. 遥感学报, 24(4): 465-478 [DOI: 10.11834/jrs.20209252http://dx.doi.org/10.11834/jrs.20209252]
Zhao C H, Li X Y and Zhu H F. 2017. Hyperspectral anomaly detection based on stacked denoising autoencoders. Journal of Applied Remote Sensing, 11(4): 042605 [DOI: 10.1117/1.JRS.11.042605http://dx.doi.org/10.1117/1.JRS.11.042605]
Zhou J, Kwan C, Ayhan B and Eismann M T. 2016. A novel cluster kernel RX algorithm for anomaly and change detection using hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 54(11): 6497-6504 [DOI: 10.1109/TGRS.201622585495http://dx.doi.org/10.1109/TGRS.201622585495]
相关文章
相关作者
相关机构
京公网安备11010802024621