Skip to main content
SpringerLink
Log in

TARDB-Net: triple-attention guided residual dense and BiLSTM networks for hyperspectral image classification

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Each sample in the hyperspectral remote sensing image has high-dimensional features and contains rich spatial and spectral information, which greatly increases the difficulty of feature selection and mining. In view of these difficulties, we propose a novel Triple-attention Guided Residual Dense and BiLSTM networks(TARDB-Net) to reduce redundant features while increasing feature fusion capabilities, which ultimately improves the ability to classify hyperspectral images. First, a novel Triple-attention mechanism is proposed to assign different weights to each feature. Then, the residual network is used to perform the residual operation on the features, and the initial features of the multiple residual blocks and the generated deep residual features are intensively fused, retaining a host number of prior features. And use the bidirectional long short-term memory network to integrate the contextual semantics of deep fusion features. Finally, the classification task is completed by Softmax classifier. Experiments on three hyperspectral datasets—Indian Pines, University of Pavia, and Salinas—show that under 10% of the training samples, the overall accuracy of our method is 87%, 96% and 96%, which is superior to several well-known methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473

  2. Bioucas-Dias et al (2013) Hyperspectral remote sensing data analysis and future challenges. IEEE Geosci. Remote Sens. Mag. 1(2):6–36

    Article  Google Scholar 

  3. Chen Y, Wan J, Zhang J, Zhao J, Ye F, Wang Z, Liu S (2019) Automatic Extraction Method of Sargassum Based on Spectral-Texture Features of Remote Sensing Images. In IGARSS 2019–2019 IEEE International Geoscience and Remote Sensing Symposium.; pp. 3705–3707

  4. Dong X, Sun X, Jia X, Xi Z, Gao L, Zhang B (2020) Remote sensing image super-resolution using novel dense-sampling networks. IEEE Trans Geosci Remote Sens

  5. El-Shafie AHA, Zaki M, Habib SED (2019) Fast CNN-based object tracking using localization layers and deep features interpolation. In 2019 15th international wireless communications and Mobile computing conference (IWCMC).; pp. 1476–1481

  6. Gao H, Yang Y, Yao D, Li C (2019) Hyperspectral image classification with pre-activation residual attention network. IEEE Access 7:176587–176599

    Article  Google Scholar 

  7. Hang R, Liu Q, Hong D, Ghamisi P (2019) Cascaded recurrent neural networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(8):5384–5394

    Article  Google Scholar 

  8. Hassaballah M, Awad AI (2020) Deep Learning in Computer Vision: Principles and Applications, CRC Presss

  9. He Q, Lee Y, Huang D, He S, Song W, Du Y (2018) Multi-modal remote sensing image classification for low sample size data. In 2018 international joint conference on neural networks (IJCNN).: pp. 1-6.

  10. Jia B et al (2020) Essential processing methods of hyperspectral images of agricultural and food products. Chemom Intell Lab Syst 198:103936

    Article  Google Scholar 

  11. Jing R, Liu S, Gong Z, Wang Z, Guan H, Gautam A, Zhao W (2020) Object-based change detection for VHR remote sensing images based on a Trisiamese-LSTM. Int J Remote Sens 41(16):6209–6231

    Article  Google Scholar 

  12. Li J, Lin D, Wang Y, Xu G, Zhang Y, Ding C, Zhou Y (2020) Deep discriminative representation learning with attention map for scene classification. Remote Sens 12(9):1366

    Article  Google Scholar 

  13. Liu, Ziwei, et al. (2020) Using convolution neural network and hyperspectral image to identify moldy peanut kernels. LWT 132 109815

  14. Paoletti ME, Haut JM, Fernandez-Beltran R, Plaza J, Plaza AJ, Pla F (2018) Deep pyramidal residual networks for spectral–spatial hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(2):740–754

    Article  Google Scholar 

  15. Raju KK, Saradhi Varma GP, Rajyalakshmi D (2020) A comprehensive review on effect of band selection on the recital of hyper-spectral image classification. Microelectronics, Electromagnetics and Telecommunications 303–320

  16. Salman M, Yüksel SE (2018) Fusion of hyperspectral image and LiDAR data and classification using deep convolutional neural networks. In 2018 26th signal processing and communications applications conference (SIU).; pp. 1–4

  17. Shumilo L, Yailymov B, Kussul N, Lavreniuk M, Shelestov A, Korsunska Y (2019) Rivne City land cover and land surface temperature analysis using remote sensing data. In 2019 IEEE 39th international conference on electronics and nanotechnology (ELNANO); pp. 813–816

  18. Sowmya V, Soman KP, Hassaballah M (2019) Hyperspectral image: fundamentals and advances. Recent Advances in Computer Vision. Springer, Cham, 401–424

  19. Su H, Yang X, Yan XH (2019) Estimating Ocean Subsurface Salinity from Remote Sensing Data by Machine Learning. In IGARSS 2019–2019 IEEE International Geoscience and Remote Sensing Symposium.; pp. 8139–8142

  20. Tao R, Zhao X, Li W, Li H-C, 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

    Article  Google Scholar 

  21. Tong XY, Xia GS, Lu Q, Shen H, Li S, You S, Zhang L (2020) Land-cover classification with high-resolution remote sensing images using transferable deep models. Remote Sens Environ 237:111322

    Article  Google Scholar 

  22. Wang Z, Zou C, Cai W (2020) Small sample classification of Hyperspectral remote sensing images based on sequential joint Deeping learning model. IEEE Access 8:71353–71363

    Article  Google Scholar 

  23. Xie F, Li F, Lei C, Yang J, Zhang Y (2019) Unsupervised band selection based on artificial bee colony algorithm for hyperspectral image classification. Appl Soft Comput 75:428–440

    Article  Google Scholar 

  24. Xu L, Chen Q (2019) Remote-sensing image usability assessment based on ResNet by combining edge and texture maps. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12(6):1825–1834

    Article  Google Scholar 

  25. Yang Z-L et al (2018) RNN-stega: linguistic steganography based on recurrent neural networks. IEEE Transactions on Information Forensics and Security 14(5):1280–1295

    Article  Google Scholar 

  26. Yang G, Gewali UB, Ientilucci E, Gartley M, Monteiro ST (2018) Dual-channel DenseNet for hyperspectral image classification. In IGARSS 2018–2018 IEEE International Geoscience and Remote Sensing Symposium.; pp. 2595–2598

  27. You H, Tian S, Yu L, Lv Y (2019) Pixel-level remote sensing image recognition based on bidirectional word vectors. IEEE Trans Geosci Remote Sens 58(2):1281–1293

    Article  Google Scholar 

  28. Zhang J, Lu C, Li X, Kim HJ, Wang J (2019) A full convolutional network based on DenseNet for remote sensing scene classification. Math Biosci Eng 16(5):3345–3367

    Article  Google Scholar 

  29. Zhang S, Yuan Q, Li J, Sun J, Zhang X (2020) Scene-adaptive remote sensing image super-resolution using a multiscale attention network. IEEE Trans Geosci Remote Sens

  30. Zhou Y, Wang M (2019) Remote sensing image classification based on AlexNet network model. In international conference on frontier computing.; pp. 913–918

  31. Zhou W et al (2020) SO–CNN based urban functional zone fine division with VHR remote sensing image. Remote Sensing of Environment 236:111458

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported by the Hunan Key Laboratory of Intelligent Logistics Technology under Grant 2019TP1015.

Author information

Authors and Affiliations

  1. School of Logistics and Transportation, Central South University of Forestry and Technology, Changsha, 410004, China

    Weiwei Cai, Zhanguo Wei & Meilin Li

  2. Changsha Astra Information Technology Co., Ltd., Changsha, 410219, China

    Weiwei Cai

  3. Central South University, Changsha, 410083, China

    Botao Liu

  4. Beijing Forestry University, Beijing, 100083, China

    Jiangming Kan

Authors
  1. Weiwei Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Botao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhanguo Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Meilin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jiangming Kan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhanguo Wei.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cai, W., Liu, B., Wei, Z. et al. TARDB-Net: triple-attention guided residual dense and BiLSTM networks for hyperspectral image classification. Multimed Tools Appl 80, 11291–11312 (2021). https://doi.org/10.1007/s11042-020-10188-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-10188-x

Keywords

Search

Navigation