浏览全部资源
扫码关注微信
Published： 07 January 2024 ，
扫 描 看 全 文
周琨，徐洋，魏洁，吴泽彬，韦志辉.2024.约束能量最小化变分自编码的高光谱目标检测.遥感学报，28（1）： 78-87
Zhou K，Xu Y，Wei J，Wu Z B and Wei Z H. 2024. Hyperspectral target detection based on constrained energy minimization variational autoencoder. National Remote Sensing Bulletin， 28（1）：78-87
目标检测是高光谱领域中一个重要的研究方向，高光谱目标检测（hyperspectral target detection）是根据目标的光谱特征将像素判断为背景或者目标。在过去的几十年中已经提出了很多的检测算法，但是高光谱图像中背景样本的复杂性以及目标样本的有限性，使得检测算法面临着很大的挑战。本文提出了一种基于背景重构的高光谱目标检测算法，利用高光谱图像中背景样本占比较大的特点，训练背景样本自表示模型，然后重构出背景。同时利用约束能量最小化对残差图像进行检测，将重构出的背景用于自相关矩阵计算，避免目标样本参与计算影响目标样本的响应能量，提高了检测的精确度。在真实的高光谱图像数据上结果明显优于对比实验，验证了该方法的有效性和高效性。
Target detection is an important research direction in the hyperspectral field. Hyperspectral target detection aims to distinguish pixels as background or target according to the spectral characteristics of the target. Several detection algorithms have been proposed in the past few decades. However
the complexity of background samples in hyperspectral images and the limited number of target samples lead to considerable challenges in detection algorithms. A hyperspectral target detection algorithm based on background reconstruction is proposed in this paper. Taking advantage of the large proportion of background samples in hyperspectral images
the self-representation model of the background samples is trained
and then the background is reconstructed. Simultaneously
the constrained energy minimization is used to detect the residual image
and the reconstructed background is used for the calculation of the correlation matrix. Therefore
the target sample is not involved in the calculation to affect the response energy of the target sample
and the detection accuracy is improved. Results on real hyperspectral image data are better than those of comparison experiments
which verify the effectiveness of this method.
Obtaining numerous training sets of artificially labeled hyperspectral data is difficult. Therefore
using limited samples to train deep neural networks is the largest difficulty in applying deep learning to hyperspectral target detection. When calculating the average output energy of the background
the calculation of the correlation matrix of all samples is used. Therefore
the target pixel also participates in the calculation
causing a certain degree of damage to the target spectrum. The background is used as a training sample to train the entire network to solve the above problems
and the reconstructed background is utilized for constrained energy minimization detection to reduce the impact on the target spectrum during the detection process.
This paper proposes a hyperspectral target detection based on constrained energy minimization variational autoencoder. First
the image is roughly detected to obtain the training background sample. The background sample then is inputted into the variational autoencoder for training. The network introduces a constraint energy minimization regularization to remove the characteristics of the target sample and help the reconstructed sample retain only the background information. The 3D residual is acquired by calculating the difference between the original image and the reconstructed background. Thus
the constraint energy minimization is used to detect the residual. The background correlation matrix is employed in the detection process to replace the residual correlation matrix. Finally
the final detection result is obtained by weighting.
Compared with other comparative experiments
the proposed method achieved good detection results. The AUC table shows that most of the six hyperspectral datasets performed better than the comparison experiments
and most of the AUC values reached more than 99%. The detection map reveals that the target part is well detected. A close ROC curve to the upper left corner yields satisfactory effects. The curve of the proposed method performs well compared with other methods.
Overall
a hyperspectral target detection based on constrained energy minimization variational autoencoder is proposed. The algorithm utilizes the characteristics of the large distribution of background pixels in hyperspectral images. First
the coarse detection is used to obtain the background samples for training. The variational autoencoder then trains the background self-representation model and reconstructs its background. A constraint energy minimization regularization is introduced to help the reconstructed samples retain only the background information. Simultaneously
when using the constraint energy minimization to detect the residual image
the background correlation matrix contributes to the calculation to prevent the participation of non-background pixels in the calculation and lose the target signal output. Experimental results on real hyperspectral datasets show that the algorithm outperforms other comparative experimental results. However
the model is highly dependent on the effect of background reconstruction. If the effect of background reconstruction is superior
then the detection rate will be high. Therefore
improving the stability of background reconstruction in the future is necessary.
遥感高光谱目标检测背景重构约束能量最小化自相关矩阵
hyperspectraltarget detectionbackground reconstructionconstrained energy minimizationcorrelation matrix
Du B, Zhang L P, Tao D C and Zhang D Y. 2013. Unsupervised transfer learning for target detection from hyperspectral images. Neurocomputing, 120: 72-82 [DOI: 10.1016/j.neucom.2012.08.056http://dx.doi.org/10.1016/j.neucom.2012.08.056]
Farrand W H and Harsanyi J C. 1997. Mapping the distribution of mine tailings in the Coeur d'Alene River Valley, Idaho, through the use of a constrained energy minimization technique. Remote Sensing of Environment, 59(1): 64-76 [DOI: 10.1016/S0034-4257(96)00080-6http://dx.doi.org/10.1016/S0034-4257(96)00080-6]
Harsanyi J C and Chang C I. 1994. Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach. IEEE Transactions on Geoscience and Remote Sensing, 32(4): 779-785 [DOI: 10.1109/36.298007http://dx.doi.org/10.1109/36.298007]
He L, Pan Q, Di W and Li Y Q. 2009. Research advance on target detection for hyperspectral imagery. Acta Electronica Sinica, 37(9): 2016-2024
贺霖, 潘泉, 邸韡, 李远清. 2009. 高光谱图像目标检测研究进展. 电子学报, 37(9): 2016-2024 [DOI: 10.3321/j.issn:0372-2112.2009.09.024http://dx.doi.org/10.3321/j.issn:0372-2112.2009.09.024]
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]
Kraut S, Scharf L L and Butler R W. 2005. The adaptive coherence estimator: a uniformly most-powerful-invariant adaptive detection statistic. IEEE Transactions on Signal Processing, 53(2): 427-438 [DOI: 10.1109/TSP.2004.840823http://dx.doi.org/10.1109/TSP.2004.840823]
Kruse F A, Lefkoff A B, Boardman J W, Heidebrecht K B, Shapiro A T, Barloon P J and Goetz A F H. 1993. The spectral image processing system (SIPS)—interactive visualization and analysis of imaging spectrometer data. Remote Sensing of Environment, 44(2/3): 145-163 [DOI: 10.1016/0034-4257(93)90013-Nhttp://dx.doi.org/10.1016/0034-4257(93)90013-N]
Li W, Du Q and Zhang B. 2015. Combined sparse and collaborative representation for hyperspectral target detection. Pattern Recognition, 48(12): 3904-3916 [DOI: 10.1016/j.patcog.2015.05.024http://dx.doi.org/10.1016/j.patcog.2015.05.024]
Liu Y N. 2021. Development of hyperspectral imaging remote sensing technology. National Remote Sensing Bulletin, 25(1): 439-459
刘银年. 2021. 高光谱成像遥感载荷技术的现状与发展. 遥感学报, 25(1): 439-459 [DOI: 10.11834/jrs.20210283http://dx.doi.org/10.11834/jrs.20210283]
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]
Manolakis D, Siracusa C and Shaw G. 2001. Hyperspectral subpixel target detection using the linear mixing model. IEEE Transactions on Geoscience and Remote Sensing, 39(7): 1392-1409 [DOI: 10.1109/36.934072http://dx.doi.org/10.1109/36.934072]
Robey F C, Fuhrmann D R, Kelly E J and Nitzberg R. 1992. A CFAR adaptive matched filter detector. IEEE Transactions on Aerospace and Electronic Systems, 28(1): 208-216 [DOI: 10.1109/7.135446http://dx.doi.org/10.1109/7.135446]
Shi Y Z, Li J J, Yin Y P, Xi B B and Li Y S. 2019. Hyperspectral target detection with macro-micro feature extracted by 3-D residual autoencoder. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(12): 4907-4919 [DOI: 10.1109/JSTARS.2019.2939833http://dx.doi.org/10.1109/JSTARS.2019.2939833]
Tong Q X, Zhang B and Zheng L F. 2006. Hyperspectral Remote Sensing-Principle, Technology and Application. Beijing: Higher Education Press: 218-238
童庆禧, 张兵, 郑兰芬. 2006. 高光谱遥感——原理、技术与应用. 北京: 高等教育出版社: 218-238
Xie W Y, Lei J, Yang J, Li Y S, Du Q and Li Z. 2020a. Deep latent spectral representation learning-based hyperspectral band selection for target detection. IEEE Transactions on Geoscience and Remote Sensing, 58(3): 2015-2026 [DOI: 10.1109/TGRS.2019.2952091http://dx.doi.org/10.1109/TGRS.2019.2952091]
Xie W Y, Zhang X, Li Y S, Wang K Y and Du Q. 2020b. Background learning based on target suppression constraint for hyperspectral target detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 5887-5897 [DOI: 10.1109/JSTARS.2020.3024903http://dx.doi.org/10.1109/JSTARS.2020.3024903]
Xie W Y, Zhong J P and Li Y S. 2022. A background memory model for hyperspectral anomaly detection. National Remote Sensing Bulletin: 1-13
谢卫莹, 钟佳平, 李云松. 2022. 面向高光谱异常检测的背景记忆模型. 遥感学报: 1-13 [DOI: 10.11834/jrs.20221241http://dx.doi.org/10.11834/jrs.20221241]
Xu Y, Wu Z B, Xiao F, Zhan T M and Wei Z H. 2016. A target detection method based on low-rank regularized least squares model for hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 13(8): 1129-1133 [DOI: 10.1109/LGRS.2016.2572090http://dx.doi.org/10.1109/LGRS.2016.2572090]
Ye Z, Bai L and He M Y. 2021. Review of spatial-spectral feature extraction for hyperspectral image. Journal of Image and Graphics, 26(8): 1737-1763
叶珍, 白璘, 何明一. 2021. 高光谱图像空谱特征提取综述. 中国图象图形学报, 26(8): 1737-1763 [DOI: 10.11834/jig.210198http://dx.doi.org/10.11834/jig.210198]
Yin J H, Sun J Y, Wang Y S and Gao C. 2012. Sample weighting constrained energy minimization algorithm. Acta Electronica Sinica, 40(4): 788-792
尹继豪, 孙建颖, 王义松, 高超. 2012. 样本加权约束能量最小化算法. 电子学报, 40(4): 788-792 [DOI: 10.3969/j.issn.0372-2112.2012.04.027http://dx.doi.org/10.3969/j.issn.0372-2112.2012.04.027]
Zhang G G, Zhao S Z, Li W, Du Q, Ran Q and Tao R. 2020. HTD-Net: a deep convolutional neural network for target detection in hyperspectral imagery. Remote Sensing, 12(9): 1489 [DOI: 10.3390/rs12091489http://dx.doi.org/10.3390/rs12091489]
Zhao R, Shi Z W, Zou Z X and Zhang Z. 2019. Ensemble-based cascaded constrained energy minimization for hyperspectral target detection. Remote Sensing, 11(11): 1310 [DOI: 10.3390/rs11111310http://dx.doi.org/10.3390/rs11111310]
Zhu D H, Du B and Zhang L P. 2021. Two-stream convolutional networks for hyperspectral target detection. IEEE Transactions on Geoscience and Remote Sensing, 59(8): 6907-6921 [DOI: 10.1109/TGRS.2020.3031902http://dx.doi.org/10.1109/TGRS.2020.3031902]
Zou Z X and Shi Z W. 2016. Hierarchical suppression method for hyperspectral target detection. IEEE Transactions on Geoscience and Remote Sensing, 54(1): 330-342 [DOI: 10.1109/TGRS.2015.2456957http://dx.doi.org/10.1109/TGRS.2015.2456957]
相关文章
相关作者
相关机构
京公网安备11010802024621