Volume 31 Issue 1
Jan.  2022
Turn off MathJax
Article Contents
MA Qiaoyu, ZHANG Xin, ZHANG Chunlei, ZHOU Heng. Hyperspectral Image Classification Based on Capsule Network[J]. Chinese Journal of Electronics, 2022, 31(1): 146-154. doi: 10.1049/cje.2021.00.056
Citation: MA Qiaoyu, ZHANG Xin, ZHANG Chunlei, ZHOU Heng. Hyperspectral Image Classification Based on Capsule Network[J]. Chinese Journal of Electronics, 2022, 31(1): 146-154. doi: 10.1049/cje.2021.00.056

Hyperspectral Image Classification Based on Capsule Network

doi: 10.1049/cje.2021.00.056
More Information
  • Author Bio:

    was born in Henan Province, China, in 1995. He received the B.E. degree in computer science and technology from Shanghai University. He is a master of engineering candidate at the School of Science, China University of Geosciences (Beijing). He research interests include deep learning and data mining. (Email: 1598974727@qq.com)

    (corresponding author) was born in Henan Province, China, in 1995. She received the B.E. degree in mathematics from China University of Geosciences (Beijing). She is a Ph.D. candidate at the School of Statistics, Beijing Normal University. Her research interests include deep learning and statistics. (Email: zhangxin1412@mail.bnu.edu.cn)

    was born in Shangdong Province, China, in 1972. He received the Ph.D. degree in Mineral Resource Prospecting and Exploration from China University of Petroleum in 2000. He is currently an Senior Engineer of China Geological Survey. His research interests include geostatistics, machine learning, and data mining. (Email: zcl_3559@126.com)

    was born in Beijing, China, in 1995. He received the B.E. degree in telecommunications engineering with management from Beijing University of Post and Telecommunication. He is a master of engineering candidate at the School of Science, China University of Geosciences (Beijing). His research interests include computer vision, deep learning, and data mining. (Email: 2119180025@cugb.edu.cn)

  • Received Date: 2021-02-03
  • Accepted Date: 2021-03-21
  • Available Online: 2021-09-24
  • Publish Date: 2022-01-05
  • The conventional convolutional neural network performs not well enough in the ground objects classification because of its insufficient ability in maintaining sensitive spectral information and characterizing the covariance of spatial structure, resulting from the narrow sensitive frequency band and complex spatial structure with diversity of hyperspectral remote sensing data which caused more serious phenomena of “same material, different spectra” and “different material, same spectra”. Therefore, an improved capsule network is proposed and introduced into hyperspectral image target recognition. A convolution structure combining shallow features and multi-scale depth features is put forward to reduce the phenomena of “different material, same spectra” firstly, and then the diversity of the spatial structure is expressed by the capsule vector and sub-capsule division in channel wise, so that the averaging effect of the convolution process is weakened in the spectral domain and the spatial domain to reduce the phenomena of “same material, different spectra”. By comparing the experimental results on the hyperspectral data sets such as Indian Pines, Salinas, Tea Tree and Xiongan, the capsule network shows strong spatial structure expression ability, flexible deep and shallow feature fusion ability in multi-scale, and its accuracy in target recognition is better than that of conventional convolutional neural networks, so it is suitable for the recognition of complex targets in hyperspectral images.
  • loading
  • [1]
    A. F. Goetz, G. Vane, J. E. Solomon, et al., “Imaging spectrometry for earth remote sensing,” Science, vol.228, no.4704, pp.1147–1153, 1985. doi: 10.1126/science.228.4704.1147
    [2]
    X. Bian, T. Zhang, L. Yan, et al., “Spatial-spectral method for classification of hyperspectral images,” Optics letters, vol.38, no.6, pp.815–817, 2013. doi: 10.1364/OL.38.000815
    [3]
    Y. Tarabalka, J. A. Benediktsson, and J. Chanussot, “Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques,” IEEE Transactions on Geoscience and Remote Sensing, vol.47, no.8, pp.2973– 2987, 2009. doi: 10.1109/TGRS.2009.2016214
    [4]
    F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. on Geoscience and Remote Sensing, vol.42, no.8, pp.1778–1790, 2004. doi: 10.1109/TGRS.2004.831865
    [5]
    Y. Luo, J. Zou, C. Yao, et al., “HSI-CNN: A novel convolution neural network for hyperspectral image,” 2018 International Conference on Audio, Language and Image Processing (ICALIP), IEEE, Shanghai, pp.464–469, 2018.
    [6]
    H Hong, W. Lihua, and S. Guangyao, “Supervised multi-manifold discriminant embedding method for hyperspectral remote sensing image classification,” Acta Electronica Sinica, vol.48, no.6, pp.1099–1107, 2020. (in Chinese)
    [7]
    Y Honggeng, T. Shengwei, Y. Long, et al., “Remote sensing image detection and segmentation based on word embedding,” Acta Electronica Sinica, vol.48, no.1, pp.75–83, 2020. (in Chinese)
    [8]
    L Yanshan, F. Leidong, and X. Weixin, “TGSIFT: Robust SIFT descriptor based on tensor gradient for hyperspectral images,” Chinese Journal of Electronics, vol.29, no.5, pp.916–925, 2020. doi: 10.1049/cje.2020.08.007
    [9]
    L Qichao, X. Liang, L. Fang, et al., “SSCDenseNet: A spectral-spatial convolutional dense network for hyperspectral image classification,” Acta Electronica Sinica, vol.48, no.4, pp.751–762, 2020. (in Chinese)
    [10]
    K. He, X. Zhang, S. Ren, et al, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp.770–778, 2016.
    [11]
    M. Seydgar, A. Alizadeh Naeini, M. Zhang, et al., “3-D convolution-recurrent networks for spectral-spatial classification of hyperspectral images,” Remote Sensing, vol.11, no.7, article no.883, 2019. doi: 10.3390/rs11070883
    [12]
    L. Mou, Y. Hua, and X. X. Zhu, “A relation-augmented fully convolutional network for semantic segmentation in aerial scenes,” in Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, pp.12416–12425, 2019.
    [13]
    Y. Du, W. Song, Q. He, et al., “Deep learning with multi-scale feature fusion in remote sensing for automatic oceanic eddy detection,” Information Fusion, vol.49, pp.89–99, 2019. doi: 10.1016/j.inffus.2018.09.006
    [14]
    W. Sun and R. Wang, “Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM,” IEEE Geoscience and Remote Sensing Letters, vol.15, no.3, pp.474–478, 2018. doi: 10.1109/LGRS.2018.2795531
    [15]
    N. Wang, F. Chen, B. Yu, et al., “Segmentation of large-scale remotely sensed images on a Spark platform: A strategy for handling massive image tiles with the MapReduce model,” ISPRS Journal of Photogrammetry and Remote Sensing, vol.162, pp.137–147, 2020. doi: 10.1016/j.isprsjprs.2020.02.012
    [16]
    K. Zhu, W. Chen, P. Ghamisi, et al., “Deep convolutional capsule network for hyperspectral image spectral and spectral-spatial classification,” Remote Sensing, vol.11, no.3, article no.223, 2019.
    [17]
    M. E. Paoletti, J. M. Haut, R. Fernandez-Beltran, et al., “Capsule networks for hyperspectral image classification,” IEEE Transactions on Geoscience and Remote Sensing, vol.57, no.4, pp.2145–2160, 2018.
    [18]
    H. Zhang, L. Meng, W. Xian, et al., “1D-convolutional capsule network for hyperspectral image classification,” arXiv preprint, arXiv: 1903.09834, 2019.
    [19]
    S. Sabour, N. Frosst, and G. E. Hinton, “Dynamic routing between capsules,” arXiv preprint, arXiv: 1710.09829, 2017.
    [20]
    G. E. Hinton, A. Krizhevsky, and S. D. Wang, “Transforming auto-encoders,” International Conference on Artificial Neural Networks, Espoo, pp.44–51, 2011.
    [21]
    C. Szegedy, L. Wei, Y. Jia, et al., “Going deeper with convolutions,” in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, pp.1–9, 2015.
    [22]
    C. Szegedy, V. Vanhoucke, S. Ioffe, et al., “Rethinking the inception architecture for computer vision,” in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp.2818–2826, 2016.
    [23]
    K. He, X. Zhang, S. Ren, et al., “Deep residual learning for image recognition,” in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp.770–778, 2016.
    [24]
    G. Huang, Z. Liu, L. Van Der Maaten, et al., “Densely connected convolutional networks,” in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, pp.4700–4708, 2017.
    [25]
    F. Khajehrayeni and H. Ghassemian, “A linear hyperspectral unmixing method by means of autoencoder networks,” International Journal of Remote Sensing, vol.42, no.7, pp.2517–2531, 2021. doi: 10.1080/01431161.2020.1854893
    [26]
    L. He, J. Zhu, J. Li, et al., “Spectral-fidelity convolutional neural networks for hyperspectral pansharpening,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol.13, pp.5898–5914, 2020. doi: 10.1109/JSTARS.2020.3025040
    [27]
    T. Alipour-Fard, M. Paoletti, J. M. Haut, et al., “Multibranch selective kernel networks for hyperspectral image classification,” IEEE Geoscience and Remote Sensing Letters, vol.18, no.6, pp.1089–1093, 2021.
    [28]
    C. Zhang, G Li, R Lei, et al., “Deep feature aggregation network for hyperspectral remote sensing image classification,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol.13, pp.5314–5325, 2020. doi: 10.1109/JSTARS.2020.3020733
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(5)  / Tables(3)

    Article Metrics

    Article views (278) PDF downloads(54) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return