Abstract
In recent years, deep learning methods have gradually come to be used in hyperspectral imaging domains. Because of the peculiarity of hyperspectral imaging, a mass of information is contained in the spectral dimensions of hyperspectral images. Also, different objects on a land surface are sensitive to different ranges of wavelength. To achieve higher accuracy in classification, we propose a structure that combines spectral sensitivity with a convolutional neural network by adding spectral weights derived from predicted outcomes before the final classification layer. First, samples are divided into visible light and infrared, with a portion of the samples fed into networks during training. Then, two key parameters, unrecognized rate (δ) and wrongly recognized rate (γ), are calculated from the predicted outcome of the whole scene. Next, the spectral weight, derived from these two parameters, is calculated. Finally, the spectral weight is added and an improved structure is constructed. The improved structure not only combines the features in spatial and spectral dimensions, but also gives spectral sensitivity a primary status. Compared with inputs from the whole spectrum, the improved structure attains a nearly 2% higher prediction accuracy. When applied to public data sets, compared with the whole spectrum, on the average we achieve approximately 1% higher accuracy.
概要
目 的
由于高光谱成像的特性, 高光谱遥感影像较光学、 多光谱影像具有更多的光谱信息, 因此对高光谱影像地物的分类也相对困难. 为提高分类精度, 本文提出一个新的高光谱遥感影像分类模型.
创新点
考虑到不同的地物覆盖对不同波段范围的电磁波有不同的敏感度, 本文提出一个基于卷积神经网络和光谱敏感度的深度学习模型, 以提高对高光谱遥感影像地物分类的准确率. 通过在最终的分类器后添加一个光谱权重, 该模型能够更准确地分类地物.
方 法
1. 将带标记的样木在光谱维度丄分为可见光和红外波段, 并将部分样本作为训练集和测试集输入到网络中进行训练. 2. 训练宂成后利用模型对全图进行预测, 弗通过部分预测结果计箅出未识别率 δ 和误识别率 γ 两个参数. 3. 利用 δ 和 γ 可计箅出不同光谱范園的光谱权重弗将其置于分类器前 (图5).
结 论
1. 模型加入光谱权重后的分类准确率较之前提高了约 2%. 2. 利用公共数据集测试后显示, 使用了光谱权重的卷积神经网络模型的分类精度比未使用光谱权重的模型高约 1%. 3. 木文结果砬示, 利用不同地物对电磁波的敏感性差别可以增加不同地物间的差异, 从而提升分类模型的性能.
Similar content being viewed by others
References
Bengio Y, Courville A, Vincent P, 2013. Representation learning: a review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8):1798–1828. https://doi.org/10.1109/TPAMI.2013.50
Bioucas-Dias JM, Plaza A, Camps-Valls G, et al., 2013. Hyperspectral remote sensing data analysis and future challenges. IEEE Geoscience and Remote Sensing Magazine, 1(2):6–36. https://doi.org/10.1109/MGRS.2013.2244672
Bishop CM, 2006. Pattern Recognition and Machine Learning. Springer, New York, USA.
Cai Y, Yang ML, Li J, 2015. Multiclass classification based on a deep convolutional network for head pose estimation. Frontiers of Information Technology & Electronic Engineering, 16(11):930–939. https://doi.org/10.1631/FITEE.1500125
Cao JY, Chen Z, Wang B, 2016. Deep convolutional networks with superpixel segmentation for hyperspectral image classification. Proceedings of 2016 IEEE International Geoscience and Remote Sensing Symposium, p.3310-3313. https://doi.org/10.1109/IGARSS.2016.7729856
Chen YS, Zhao X, Jia XP, 2015. Spectral-spatial classification of hyperspectral data based on deep belief network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6):2381–2392. https://doi.org/10.1109/JSTARS.2015.2388577
Du B, Zhang LP, 2014. A discriminative metric learning based anomaly detection method. IEEE Transactions on Geoscience and Remote Sensing, 52(11):6844–6857. https://doi.org/10.1109/TGRS.2014.2303895
Glorot X, Bordes A, Bengio Y, 2011. Deep sparse rectifier neural networks. Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, p.315-323.
Gu YF, Chanussot J, Jia XP, et al., 2017. Multiple kernel learning for hyperspectral image classification: a review. IEEE Transactions on Geoscience and Remote Sensing, 55(11):6547–6565. https://doi.org/10.1109/TGRS.2017.2729882
Hinton GE, Salakhutdinov RR, 2006. Reducing the dimensionality of data with neural networks. Science, 313(5786):504–507. https://doi.org/10.1126/science.1127647
Hotelling H, 1933. Analysis of a complex of statistical variables into principal components. Journal of Educational Psychology, 24(6):417–441. https://doi.org/10.1037/h0071325
Krizhevsky A, Sutskever I, Hinton GE, 2017. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90. https://doi.org/10.1145/3065386
LeCun Y, Boser B, Denker JS, et al., 1989. Backpropagation applied to handwritten zip code recognition. Neural Computation, 1(4):541–551. https://doi.org/10.1162/neco.1989.1.4.541
Li J, Bioucas-Dias JM, Plaza A, 2010. Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning. IEEE Transactions on Geoscience and Remote Sensing, 48(11):4085–4098. https://doi.org/10.1109/TGRS.2010.2060550
Li YS, Xie WY, Li HQ, 2017. Hyperspectral image reconstruction by deep convolutional neural network for classification. Pattern Recognition, 63:371–383. https://doi.org/10.1016/j.patcog.2016.10.019
McCulloch WS, Pitts W, 1943. A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics, 5(4):115–133. https://doi.org/10.1007/BF02478259
Melgani F, Bruzzone L, 2004. Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(8):1778–1790. https://doi.org/10.1109/TGRS.2004.831865
Mou LC, Ghamisi P, Zhu XX, 2017. Deep recurrent neural networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 55(7):3639–3655. https://doi.org/10.1109/TGRS.2016.2636241
Onojeghuo AO, Blackburn GA, Huang JF, et al., 2018. Applications of satellite ‘hyper-sensing’ in Chinese agriculture: challenges and opportunities. International Journal of Applied Earth Observation and Geoinformation, 64:62–86. https://doi.org/10.1016/j.jag.2017.09.005
Rosenblatt F, 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, 65(6):386–408. https://doi.org/10.1037/h0042519
Rumelhart DE, Hinton GE, Williams RJ, 1988. Learning internal representations by error propagation. In Collins A, Smith EE (Eds.), Readings in Cognitive Science. Morgan Kaufmann, San Mateo, USA. https://doi.org/10.1016/B978-1-4832-1446-7.50035-2
Sigurdsson J, Ulfarsson MO, Sveinsson JR, 2014. Semi-supervised hyperspectral unmixing. Proceedings of 2014 IEEE Geoscience and Remote Sensing Symposium, p.3458-3461. https://doi.org/10.1109/IGARSS.2014.6947226
Szegedy C, Vanhoucke V, Ioffe S, et al., 2016. Rethinking the inception architecture for computer vision. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, p.2818-2826. https://doi.org/10.1109/CVPR.2016.308
Wang LD, Zhou W, Xing Y, et al., 2019. A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG. Frontiers of Information Technology & Electronic Engineering, 20(3):405–413. https://doi.org/10.1631/FITEE.1700413
Wentz EA, Anderson S, Fragkias M, et al., 2014. Supporting global environmental change research: a review of trends and knowledge gaps in urban remote sensing. Remote Sensing, 6(5):3879–3905. https://doi.org/10.3390/rs6053879
Yang XH, Huang JF, Wang FM, et al., 2006. A modified chlorophyll absorption continuum index for chlorophyll estimation. Journal of Zhejiang University-SCIENCE A, 7(12):2002–2006. https://doi.org/10.1631/jzus.2006.A2002
Ye CM, Cui P, Pirasteh S, et al., 2017. Experimental approach for identifying building surface materials based on hyperspectral remote sensing imagery. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 18(12):984–990. https://doi.org/10.1631/jzus.A1700149
Zhang F, Du B, Zhang LP, et al., 2016. Hierarchical feature learning with dropou. k-means for hyperspectral image classification. Neurocomputing, 187:75–82. https://doi.org/10.1016/j.neucom.2015.07.132
Zhao WZ, Du SH, 2016. Learning multiscale and deep representations for classifying remotely sensed imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 113:155–165. https://doi.org/10.1016/j.isprsjprs.2016.01.004
Zhong P, Gong ZQ, Li ST, et al., 2017. Learning to diversify deep belief networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 55(6):3516–3530. https://doi.org/10.1109/TGRS.2017.2675902
Zhong ZL, Li J, Luo ZM, et al., 2018. Spectral-spatial residual network for hyperspectral image classification: a 3-D deep learning framework. IEEE Transactions on Geoscience and Remote Sensing, 56(2):847–858. https://doi.org/10.1109/TGRS.2017.2755542
Author information
Authors and Affiliations
Contributions
Cheng-ming YE designed the research. Xin LIU and Hong XU processed the corresponding data. Xin LIU and Cheng-ming YE wrote the first draft of the manuscript. Jonathan LI and Hong XU helped organize the manuscript. Xin LIU, Yao LI, Shi-cong REN, and Jonathan LI revised and edited the final version.
Corresponding author
Ethics declarations
Cheng-ming YE, Xin LIU, Hong XU, Shi-cong REN, Yao LI, and Jonathan LI declare that they have no conflict of interest.
Additional information
Project supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (No. XDA23090203), the National Key Technologies Research and Development Program of China (No. 2016YFB0502600), and the Key Program of Sichuan Bureau of Science and Technology (No. 2018SZ0350), China
Rights and permissions
About this article
Cite this article
Ye, Cm., Liu, X., Xu, H. et al. Classification of hyperspectral images based on a convolutional neural network and spectral sensitivity. J. Zhejiang Univ. Sci. A 21, 240–248 (2020). https://doi.org/10.1631/jzus.A1900085
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/jzus.A1900085