Abstract
Deep learning frameworks have been applied to hyperspectral image classification (HIC) problems more and more in recent years, with excellent results. Existing network models, on the other hand, have a higher model complexity and take more time. The link between local spatial features is often overlooked in traditional HIC algorithms. This article presents a novel Lightweight Cascaded Deep Convolutional Neural Network (LC-DCNN) that describes the spatial as well as spectral characteristics of the hyperspectral images. The performance of the proposed LC-DCNN is validated for different spectral band reductions techniques to minimize the computational complexity of HIC such as Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA). The effectiveness of the proposed algorithm is validated on the Indian Pines and Salinas dataset for the vegetation and agriculture detection field based on accuracy, recall, precision and F1-score. The proposed approach provides 99% and 99.63% accuracy over Indian Pines and Salinas datasets, respectively, over the traditional state of arts employed previously for the HIC. The performance of the suggested LC-DCNN decreases for a larger number of classes. In the future, the performance can be improved for the real time dataset by considering a larger dataset consisting of larger objects.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bai, J., Ding, B., Xiao, Z., Jiao, L., Chen, H., & Regan, A. C. (2022). HIC based on deep attention graph convolutional network. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–16. https://doi.org/10.1109/TGRS.2021.3066485
Chang, Y.-L., Tan, T.-H., Lee, W.-H., Chang, L., Chen, Y.-N., Fan, K.-C., & Alkhaleefah, M. (2022). Consolidated convolutional neural network for HIC. Remote Sensing, 14(7), 1571. https://doi.org/10.3390/rs14071571.
Chen, Y., Wang, Y., Gu, Y., He, X., Ghamisi, P., & Jia, X. (2019). Deep learning ensemble for HIC. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(6), 1882–1897. https://doi.org/10.1109/JSTARS.2019.2915259.
Diakite, Alou, G., & Fu, X. (2021). HIC using 3D 2D CNN. IET Image Processing, 15(5), 1083–1092. https://doi.org/10.1049/ipr2.12087.
Gao, H., Chen, Z., & Li, C. (2021). Sandwich convolutional neural network for HIC using spectral feature enhancement. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 3006–3015. https://doi.org/10.1109/JSTARS.2021.3062872.
Ghaderizadeh, S., DariushAbbasi-Moghadam, A., Zhao, N., & Tariq, A. (2021). HIC using a hybrid 3D–2D convolutional neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 7570–7588. https://doi.org/10.1109/JSTARS.2021.3099118.
Guo, Y., Yin, X., Zhao, X., Yang, D., & Bai, Yu. (2019). HIC with SVM and guided filter. EURASIP Journal on Wireless Communications and Networking, 2019(1), 1–9. https://doi.org/10.1186/s13638-019-1346-z.
Imani, M., & Ghassemian, H. (2020). An overview on spectral and spatial information fusion for HIC: Current trends and challenges. Information Fusion, 59, 59–83. https://doi.org/10.1016/j.inffus.2020.01.007.
Jia, S., Jiang, S., Lin, Z., Li, N., Xu, M., & Yu, S. (2021). A survey: Deep learning for HIC with few labeled samples. Neurocomputing, 448(2021), 179–204. https://doi.org/10.1016/j.neucom.2021.03.035.
Lv, W., & Wang, X. (2020). Overview of HIC. Journal of Sensors, 2020, 1–13. https://doi.org/10.1155/2020/4817234.
Ortac, G., & Ozcan, G. (2021). Comparative study of HIC by multidimensional convolutional neural network approaches to improve accuracy. Expert Systems with Applications, 182, 115280. https://doi.org/10.1016/j.eswa.2021.115280.
Tu, B., Wang, J., Kang, X., Zhang, G., Ou, X., & Guo, L. (2018). KNN-based representation of superpixels for HIC. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11, 4032–4047. https://doi.org/10.1109/JSTARS.2018.2872969.
Villa, J. A., Benediktsson, J. C., & Jutten, C. (2011). HIC with independent component discriminant analysis. IEEE Transactions Geoscience Remote Sensing, 49(12), 4865–4876. https://doi.org/10.1109/TGRS.2011.2153861.
Xia, C., Yang, S., Huang, M., Zhu, Q., Guo, Y., & Qin, J. (2019). Maize seed classification using hyperspectral image coupled with multi-linear discriminant analysis. Infrared Physics & Technology, 103, 103077. https://doi.org/10.1016/j.infrared.2019.103077.
Xie, F., Gao, Q., Jin, C., & Zhao, F. (2021). HIC based on superpixel pooling convolutional neural network with transfer learning. Remote Sensing, 13(5), 930. https://doi.org/10.3390/rs13050930.
Yuan, Y., Wang, C., & Jiang, Z. (2021). Proxy-based deep learning framework for spectral–spatial HIC: Efficient and robust. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–15. https://doi.org/10.1109/TGRS.2021.3054008.
Yao, Ding, Zhang Zhi-li, Zhao Xiao-feng, Cai Wei, He Fang, Cai Yao-ming, and Wei-Wei Cai. “Deep hybrid: Multi-graph neural network collaboration for HIC.” Defence Technology (2022). https://doi.org/10.1016/j.dt.2022.02.007.
Zheng, J., YuchaoFeng, C. B., & Zhang, J. (2020). HIC using mixed convolutions and covariance pooling. IEEE Transactions on Geoscience and Remote Sensing, 59(1), 522–534. https://doi.org/10.1109/TGRS.2020.2995575.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We have no conflict of interest to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Shinde, S., Patidar, H. Hyperspectral Image Classification for Vegetation Detection Using Lightweight Cascaded Deep Convolutional Neural Network. J Indian Soc Remote Sens 51, 2159–2166 (2023). https://doi.org/10.1007/s12524-023-01754-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12524-023-01754-5