Skip to main content

Advertisement

SpringerLink
Log in

Enhancing remote target classification in hyperspectral imaging using graph attention neural network

  • Published:
Journal of Earth System Science Aims and scope Submit manuscript

Abstract

The method of target classification known as hyperspectral imaging (HSI) is commonly used in the field of remote sensing. However, recent research has shown that categorizing HSI can be problematic due to the limited availability of labelled data. There is significant interest in applying this technique to hyperspectral data. Previous graph neural network (GNN)-based methodologies often used a graph filter to obtain HSI properties, but the potential advantages of various graph neural networks and graph filters have not been fully exploited. GNNs often operate under the assumption that a node’s neighbours are independent of each other, neglecting potential interactions among them. To overcome these limitations, graph attention neural network-based remote target classification (GANN-RTC) has been proposed. It has the ability to handle both the labelled and unlabelled datasets. To evaluate the performance of GANN-RTC, we compared it with existing methods using performance measures such as individual class accuracy, overall accuracy, and the Kappa coefficient. The findings indicate that the GANN-RTC yields enhancements in OA, ICA, and KC by 2.32, 7.89, and 2.47% for the Cuprite dataset and 4.79, 11.85, and 2.82% for the Pavia University dataset.

Research highlights

  • The research focuses on remote target classification in hyperspectral imaging using a Graph Attention Neural Network.

  • Previous methods in this field have not fully utilized the potential advantages of graph filters and graph neural networks.

  • The proposed approach overcomes limitations by considering interactions between neighbouring nodes and can handle both labelled and unlabelled datasets.

  • Performance evaluation shows significant improvements in overall accuracy, individual class accuracy, and the Kappa coefficient compared to existing state-of-the-art 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

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9

Similar content being viewed by others

References

  • Atiya K, Amol D V, Shankar M and Patil C H 2022 A systematic review on hyperspectral imaging technology with a machine and deep learning methodology for agricultural applications; Ecol. Inform. 69 1–14, https://doi.org/10.1016/j.ecoinf.2022.101678.

    Article  Google Scholar 

  • Bai J, Shi W, Xiao Z, Ali T A A, Ye F and Jiao L 2023 Achieving better category separability for hyperspectral image classification: A spatial–spectral approach; IEEE Trans. Neural Netw. Learn. Syst. 1–15, https://doi.org/10.1109/TNNLS.2023.3235711.

  • Banerjee A and Banik D 2023 Resnet based hybrid convolution LSTM for hyperspectral image classification; Multimed. Tools Appl. 1–13, https://doi.org/10.1007/s11042-023-16241-9.

  • Beatty G, Kochis E and Bloodgood M 2019 The use of unlabeled data versus labeled data for stopping active learning for text classification; IEEE Int. Conf. on Semantic Computing (ICSC), Newport Beach, CA, USA, pp. 287–294, https://doi.org/10.1109/ICOSC.2019.8665546.

  • Chellaswamy C, Ganesh Babu R, Saravanan M, Abirami M, Boosuphasri R and Manjalam Balaji 2020 Machine learning based condition recognition system for bikers; IEEE 7th Int. Conf. on Smart Structures and Systems, pp. 1–6, https://doi.org/10.1109/ICSSS49621.2020.9202245.

  • Chen Y, Jiang H, Li C, Jia X and Ghamisi P 2016 Deep feature extraction and classification of hyperspectral images based on convolutional neural networks; IEEE Trans. Geosci. Remote Sens. 54 6232–6251.

    Article  Google Scholar 

  • Cui B, Peng Y, Zhang H, Li W and Du P 2023 Characterizing Markov random fields and coefficient of variations as measures of spatial distributions for hyperspectral image classification; IEEE Geosci. Remote Sens. Lett. 20 1–5, https://doi.org/10.1109/LGRS.2023.3316262.

    Article  Google Scholar 

  • Dataset: University of the Basque Country 2022 Hyperspectral Remote Sensing Scenes [Dataset]. Retrieved from http://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes.

  • De Aquino Afonso B K and Berton L 2021 Optimizing diffusion rate and label reliability in a graph-based semi-supervised classifier; In: Intelligent Systems. BRACIS 2021. Lecture Notes in Computer Science (eds) Britto A and Valdivia Delgado K, 13073, Springer, Cham., https://doi.org/10.1007/978-3-030-91702-9_34.

  • Ding Y, Zhao X, Zhang Z, Cai W and Yang N 2021 Multiscale graph sample and aggregate network with context-aware learning for hyperspectral image classification; IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 14 4561–4572, https://doi.org/10.1109/JSTARS.2021.3074469.

    Article  Google Scholar 

  • Ding Yao, Zhang Zhili, Zhao Xiaofeng, Hong Danfeng, Cai Wei, Yang Nengjun and Wang Bei 2023 Multi-scale receptive fields: Graph attention neural network for hyperspectral image classification; Expert Syst. Appl. 223 1–17, https://doi.org/10.1016/j.eswa.2023.119858.

    Article  Google Scholar 

  • Dozat T 2015 Incorporating Nesterov Momentum into Adam. [Online]. Available: http://cs229.stanford.edu/proj2015/054_report.pdf.

  • El Masry G and Sun D W 2010 Principles of hyperspectral imaging technology; In: Hyperspectral imaging for food quality analysis and control, Academic Press, pp. 3–43.

  • Ganesh Babu R and Chellaswamy C 2022 Different stages of disease detection in squash plant based on machine learning; J. Biosci. 47 1–16, https://doi.org/10.1007/s12038-021-00241-8.

    Article  Google Scholar 

  • Giri R N, Janghel R R, Pandey S K, Govil H and Sinha A 2023 Enhanced hyperspectral image classification through pretrained CNN model for robust spatial feature extraction; J. Opt., https://doi.org/10.1007/s12596-023-01473-7.

    Article  Google Scholar 

  • Haagsma M, Hagerty C H, Kroese D R and Selker J S 2023 Detection of soil-borne wheat mosaic virus using hyperspectral imaging: From lab to field scans and from hyperspectral to multispectral data; Precision Agric. 24 1030–1048, https://doi.org/10.1007/s11119-022-09986-0.

    Article  Google Scholar 

  • Hitendra Sarma T and Kakarla S 2022 A new CNN for pixel classification in hyperspectral images; In: Proceedings of International Conference on Data Science and Applications. Lecture Notes in Networks and Systems (eds) Saraswat M, Roy S, Chowdhury C and Gandomi A H, 287, Springer, Singapore, https://doi.org/10.1007/978-981-16-5348-3_61.

  • Hu H, Yao M, He F and Zhang F 2022 Graph neural network via edge convolution for hyperspectral image classification; IEEE Geosci. Remote Sens. Lett. 19 1–5, https://doi.org/10.1109/LGRS.2021.3108883.

    Article  Google Scholar 

  • Jiang X et al. 2020 Hyperspectral Image Classification with CapsNet and Markov Random Fields; IEEE Access 8 191,956–191,968, https://doi.org/10.1109/ACCESS.2020.3029174.

    Article  Google Scholar 

  • Jiao J, Yin C and Teng F 2023 W-net: Deep Convolutional Network with Gray-Level Co-occurrence Matrix and Hybrid Loss Function for Hyperspectral Image Classification; In: Advanced intelligent computing technology and applications. ICIC 2023. Lecture Notes in Computer Science (eds) Huang D S, Premaratne P, Jo K H and Hussain A, 14090, Springer, Singapore, https://doi.org/10.1007/978-981-99-4761-4_10.

  • Kamruzzaman M and Sun D W 2016 Introduction to hyperspectral imaging technology; In: Computer vision technology for food quality evaluation, pp. 111–139.

  • Kerekes J P and Baum J E 2003 Hyperspectral imaging system modeling; Linc. Lab. J. 14 117–130.

    Google Scholar 

  • Khosravi K, Rezaie F, Cooper J R, Kalantari Z, Abolfathi S and Hatamiafkoueieh J 2023 Soil water erosion susceptibility assessment using deep learning algorithms; J. Hydro. 618 1–15, https://doi.org/10.1016/j.jhydrol.2023.129229.

    Article  Google Scholar 

  • Li Y, Zhang H and Shen Q 2017 Spectral–spatial classification of hyperspectral imagery with 3D convolutional neural network; Remote Sens. 9 1–15.

    Google Scholar 

  • Luo Y, Zou J, Yao C, Zhao X, Li T and Bai G 2018 HSI-CNN: A novel convolution neural network for hyperspectral image; In: 2018 International Conference on Audio Language and Image Processing (ICALIP), Shanghai, China, pp. 464–469, https://doi.org/10.1109/ICALIP.2018.8455251.

  • MathWorks 2022 Monitor Deep Learning Training Progress. Retrieved December, 2023, from https://la.mathworks.com/help/deeplearning/ug/monitor-deep-learning-training-progress.htm.

  • Mou L, Lu X, Li X and Zhu X X 2020 Nonlocal graph convolutional networks for hyperspectral image classification; IEEE Trans. Geosci. Remote Sens. 58 8246–8257, https://doi.org/10.1109/TGRS.2020.2973363.

    Article  Google Scholar 

  • Panda A and Pradhan D 2015 Hyperspectral image processing for target detection using spectral angle mapping; In: Proceedings of the IEEE Int. Conf. Indus. Instru. Cont. (ICIC), pp. 1098–1103, https://doi.org/10.1109/IIC.2015.7150911.

  • Patel Nathan T P, Michaela G, Leblanc Mathias J R, Lane Magan R, Hoareau Guillaume L, Austin Johnson M, Jordan James E, Neff Lucas P and Williams Timothy K 2022 Endovascular perfusion augmentation after resuscitative endovascular balloon occlusion of the aorta improves renal perfusion and decreases vasopressors; J. Surg. Res. 279 712–721, https://doi.org/10.1016/j.jss.2022.06.067.

    Article  Google Scholar 

  • Prasanth S and Ratnakar D 2021 Ensemble of multiple CNN classifiers for HSI classification with superpixel smoothing; Comput. Geosci. 154 104806, https://doi.org/10.1016/j.cageo.2021.104806.

    Article  Google Scholar 

  • Qin A, Shang Z, Tian J, Wang Y, Zhang T and Tang Y 2019 Spectral–spatial graph convolutional networks for semisupervised hyperspectral image classification; Geosci. Remote Sens. Lett. IEEE 16 241–245.

    Article  Google Scholar 

  • Ravikanth L, Jayas D S, White N D G, Fields P G and Sun D W 2017 Extraction of spectral information from hyperspectral data and application of hyperspectral imaging for food and agricultural products; Food Bioprocess Technol. 10 1–33, https://doi.org/10.1007/s11947-016-1817-8.

    Article  CAS  Google Scholar 

  • Sha A, Wang B, Wu X, Zhang L, Hu B and Zhang J Q 2019 Semi-supervised classification for hyperspectral images using edge-conditioned graph convolutional networks; In: IEEE International Geoscience Remote Sensing Symposium, Yokohama, Japan, pp. 2690–2693, https://doi.org/10.1109/IGARSS.2019.8898688.

  • Sopidis G, Haslgrübler M and Ferscha A 2023 Counting activities using weakly labeled raw acceleration data: A variable-length sequence approach with deep learning to maintain event duration flexibility; Sensors 23 1–16, https://doi.org/10.3390/s23115057.

    Article  Google Scholar 

  • Umer M, Imtiaz Z, Ahmad M, Nappi M, Medaglia C, Choi G S and Mehmood A 2023 Impact of convolutional neural network and FastText embedding on text classification; Multimed. Tools Appl. 82 5569–5585, https://doi.org/10.1007/s11042-022-13459-x.

    Article  Google Scholar 

  • Velickovic P, Cucurull G, Casanova A, Romero A, Lio P and Bengio Y 2018 Graph Attention Networks; arXiv preprint arXiv: 1710.10903.

  • Vo-Dinh T 2004 A hyperspectral imaging system for in vivo optical diagnostics; IEEE Eng. Med. Bio. Mag. 23 40–49, https://doi.org/10.1109/MEMB.2004.1360407.

    Article  Google Scholar 

  • Wan S, Gong C, Zhong P, Du B, Zhang L and Yang J 2020 Multiscale dynamic graph convolutional network for hyperspectral image classification; IEEE Trans. Geosci. Remote Sens. 58 3162–3177, https://doi.org/10.1109/TGRS.2019.2949180.

    Article  Google Scholar 

  • Wang X, Kun T, Pejun D, Bo H and Jianwei D 2023a A capsule-vectored neural network for hyperspectral image classification; Knowl. Based Syst. 268 110482, https://doi.org/10.1016/j.knosys.2023.110482.

    Article  Google Scholar 

  • Wang J, Jinyue S, Erlei Z, Tian Z, Kai Y and Jinye P 2023b Hyperspectral image classification via deep network with attention mechanism and multigroup strategy; Expert Syst. Appl. 224 119904, https://doi.org/10.1016/j.eswa.2023.119904.

    Article  Google Scholar 

  • Xiao Y, Chen S, Wang H, Zhao Z, Huang T, Liang Y, Qin J, Ma R, Yin Z, Yan R and Yu X 2021 HSGACN: Hyperspectral image classification algorithm based on graph convolutional network; In: IEEE International Geoscience Remote Sensing Symposium, Brussels, Belgium, pp. 3677–3680, https://doi.org/10.1109/IGARSS47720.2021.9553449.

  • Xu Xiaoxi, Chang Qi, Pan Chundi and Cao Guo 2022 Feature fusion: Graph attention network and CNN combing for hyperspectral image classification; In: ICCCV '22: Proceedings of the 5th International Conference on Control and Computer Vision, pp. 171–178, https://doi.org/10.1145/3561613.3561640.

  • Zhang C, Li G and Du S 2019 Multi-scale dense networks for hyperspectral remote sensing image classification; IEEE Trans. Geosci. Remote Sens. 57 9201–9222.

    Article  Google Scholar 

  • Zhe W, Jianjun L, Jinlong Y, Zhiyong X and Liang X 2021 Composite kernel learning network for hyperspectral image classification; Int. J. Remote Sens. 42(16) 6066–6089, https://doi.org/10.1080/01431161.2021.1934599.

    Article  Google Scholar 

  • Zhu X X, Tuia D, Mou L, Xia G S, Zhang L, Xu F and Fraundorfer F 2017 Deep learning in remote sensing: A comprehensive review and list of resources; IEEE Geosci. Remote Sens. Mag. 5 8–36.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, SA Engineering College, Chennai, 600 077, India

    T S Geetha

  2. Department of Electronics and Communication Engineering, Prasad V Potluri Siddhartha Institute of Technology, Kanuru, Vijayawada, 520 007, India

    C Subba Rao

  3. Department of Electronics and Communication Engineering, SRM TRP Engineering College, Tiruchirappalli, 621 105, India

    C Chellaswamy & K Umamaheswari

Authors
  1. T S Geetha
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. C Subba Rao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. C Chellaswamy
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. K Umamaheswari
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

T S Geetha: Conceptualization, formal analysis, investigation; C Subba Rao: Conceptualization, methodology, analysis; C Chellaswamy: Writing draft, methodology, project administration, and resources; K Umamaheswari: Literature review, revision, and project administration.

Corresponding author

Correspondence to C Chellaswamy.

Additional information

Communicated by Saumitra Mukherjee

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Geetha, T.S., Rao, C.S., Chellaswamy, C. et al. Enhancing remote target classification in hyperspectral imaging using graph attention neural network. J Earth Syst Sci 133, 89 (2024). https://doi.org/10.1007/s12040-024-02294-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12040-024-02294-3

Keywords

Search

Navigation