Deep Feature Learning And Classification Of Remote Sensing Images
Abstract
Abstract Views: 524
Hyperspectral imaging has been largely utilized in applications involving remote sensing to describe the composition of thousands of spectral bands in a single scene. Hyperspectral images (HSI) require an accurate training model for extracting the characteristics of scenes presented in an image. Image learning models involving spectral resolution present major challenges because of the complex nature of image frames. Several attempts have been made to address this complexity. Nevertheless, these models have failed to retain a deeper understanding of hyperspectral images. Since there are mixed pixels, limited training samples, and duplicate data, so the deep learning method solves the problem.In this method, spectral values (for every pixel) of the hyperspectral images are sequentially fed into spectral long-short-term memory (LSTM) through several routes to study the spectral features. Most of the existing state-of-the-art models are based on spectral-spatial frameworks. The added spatial features add more dimensions to hyperspectral images. However, these classification models do not take advantage of the sequential nature of these images. Due to the presence of mixed pixels, limited training samples, and redundant data, the utilization of deep learning techniques addresses the problems. This paper describes a method for the classification of hyperspectral images through spectral-spatial LSTM networks. For extracting the first principal constituent from such an image, principle component analysis (PCA) was used in spectral and spatial joint feature networks (SSJFN), as well as spectral and spatial individual extraction of the features via LSTM, to get the uniform end-to-end network. Furthermore, it was aimed to achieve the integration of all processes in a neural network by making a classifier to overcome the training error and backpropagation, which may lead to learning more features. During categorization, SoftMax classification considers the spatial and spectral characteristics of all the pixels independently to get two different outcomes. Afterwards, joint spectral-spatial results are gained by using the strategy of decision fusion. The classification accuracy improves by 2.69%, 1.53%, and 1.08% when compared to the rest of the state-of-art methods.
Downloads
References
L. Mou, P. Ghamisi, and X. X. Zhu, “Deep recurrent neural network for hyperspectral image classification,” IEEE Transac. Geosci. Remote Sens., vol. 55, no. 7, pp. 3639-3655, 2007, doi: https://doi.org/10.1109/TGRS.2016.2636241
S. Singh and S. S. Kasana, “Spectral-Spatial hyperspectral image classification using deep learning,” presented at the 2019 Amity Int. Conf. Artif. Intell., Dubai, United Arab Emirates, Feb. 04-06, 2019, doi: https://doi.org/10.1109/AICAI.2019.8701243
R. Hang et al., “Robust matrix discriminative analysis for feature extraction from hyperspectral images,” IEEE J. Trans.Geosci. Remote Sens., vol. 10, no. 5, pp. 202-211, May. 2017, doi:
https://doi.org/10.1109/JSTARS.2017.2658948
H. Tulapurkar, B. Banerjee, and B. K. Mohan, “Effective and efficient dimensionality reduction of hyperspectral image using CNN and LSTM network,” presented at 2020 IEEE India Geosci. Remote Sens. Symp., Dec. 01-04, 2020, pp. 213-216, doi: https://doi.org/10.1109/InGARSS48198.2020.9358957
R. Hang , Q. Liu , H. Song , Y. Sun , F. Zhu , and H. Pei, “Graph regularized nonlinear ridge regression for remote sensing data analysis,” IEEE J. Select. Top. Appl. Earth Obser. Remote Sens., vol. 10, no. 1, pp. 277–285, Jan. 2017, doi: https://doi.org/10.1109/JSTARS.2016.2574802
M. Ghassemi, H. Ghassemian, and M. Imani, “Deep belief network for feature fusion in Hyperspectral image Classification,” presented at the IEEE Int. Conf. Aerospace Elect. Remote Sens. Technol.,
Sep. 20-21, 2018, doi: https://doi.org/10.1109/ICARES.2018.8547136
B. N. Soomro, L. Xiao, S. H. Soomro, and M. Molaei, “Bilayer elastic net regression model for supervised spectral-spatial hyperspectral image classification,” IEEE J. Select. Topics Appl. Earth Obser. Remote Sens., vol. 9, no. 9, pp. 4102-4116, Sept. 2016, doi: https://doi.org/10.1109/JSTARS.2016.2559524
W. Zhao and S. Du, “Spectral- Spatial feature extraction for hyperspectral image classification: A dimension reduction and deep learning approach,” IEEE Transac. Geosci. Remote Sens., vol. 54, no. 8, pp. 4544-4554, Aug. 2016, doi: https://doi.org/10.1109/TGRS.2016.2543748
W. Li, G. Wu, F. Zhang, and Q. Du, “Hyperspectral image classification using deep pixel-pair features,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 2, pp. 844–853, Feb. 2017a, doi: https://doi.org/10.1109/TGRS.2016.2616355
Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,”Nature,
vol. 521, pp. 436-444, May 2015, doi: https://doi.org/10.1038/nature14539
M. Xu, Y. Wu, P. Lv, H. Jiang, M. Luo, and Y. Ye, “miSFM: on combination of mu- tual information and social force model towards simulating crowd evacuation,” Neurocomputing, vol. 168, pp. 529-537, Nov. 2015, doi: https://doi.org/10.1016/j.neucom.2015.05.074
W. Li, G. Wu, and Q. Du, “Transferred deep learning for anomaly detection in hyper- spectral imagery,” IEEE Geosci. Remote Sens. Lett., vol. 14, no. 5, pp. 597-601, May 2017b, doi: https://doi.org/10.1109/LGRS.2017.2657818
Y. Chen, H. Jiang, C. Li, and X. Jia, “Deep feature extraction and classification of hy- per spectral images based on convolutional neural networks,” IEEE Trans. Geosci. Remote Sens., vol. 54, no. 10, pp.1-20, Oct. 2016, doi: https://doi.org/10.1109/TGRS.2016.2584107
R. Girshick, “Fast r-cnn,” Proc. IEEE Int. Conf. Comput. Vision, 2015, pp. 1440-1448.
X. Xu, W. Li, Q. Ran, Q. Du, L. Gao, and B. Zhang, “Multisource remote sensing data classification based on convolutional neural network,” IEEE Trans. Geosci. Re- mote Sens., vol. 56, no. 2, pp. 937-949, Feb. 2018, doi: https://doi.org/10.1109/TGRS.2017.2756851
Q. Liu, R. Hang, H. Song, and Z. Li , “Learning multiscale deep features for high-reso- lution satellite image scene classification,” IEEE Trans. Geosci. Remote Sens., vol. 56, no. 1, pp. 117-126, Jan. 2018, doi: https://doi.org/10.1109/TGRS.2017.2743243
Y. Chen, X. Zhao, and X. Jia, “Spectral-spatial classification of hyperspectral data based on deep belief network,” IEEE J. Select. Top. Appl. Earth Obser. Remote Sens., vol. 8, no. 6, pp. 2381-2392, June 2015, doi: https://doi.org/10.1109/JSTARS.2015.2388577
C. Tao, H. Pan, Y. Li, and Z. Zou, “Unsupervised spectral-spatial feature learning with stacked sparse autoencoder for hyperspectral imagery classification,” IEEE Geosci. Remote Sens. Lett., vol. 12, no.12, pp. 2438-2442, Dec. 2015, doi:
https://doi.org/10.1109/LGRS.2015.2482520
W. Zhao and S. Du, “Spectral-spatial feature extraction for hyperspectral image classification: A dimension reduction and deep learning approach,” IEEE Trans. Geosci. Remote Sens., vol. 54, no. 8, pp. 4544-4554, Aug. 2016, doi: https://doi.org/10.1109/TGRS.2016.2543748
Q. Liu, F. Zhou, R. Hang, and X. Yuan, “Bidirectional-convolutional lstm based spec- tral-spatial feature learning for hyperspectral image classification,” Remote Sens., vol. 9, no. 12, pp. e1330, Dec. 2017, doi: https://doi.org/10.3390/rs9121330
H. Wu and S. Prasad, “Convolutional recurrent neural networks for hyperspectral data classification,” Remote Sens., vol. 9, no. 3, pp. e298, Mar. 2017, doi: https://doi.org/10.3390/rs9030298
Z. C. Lipton, J. Berkowitz, and C. Elkan, “A critical review of recurrent neural net- works
for sequence learning,” arVix, 2015, doi: https://doi.org/10.48550/arXiv.1506.00019
D. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv, 2015, doi; https://doi.org/10.48550/arXiv.1412.6980
Y. Zhou, J. Peng, and C. L. P. Chen, “Dimension reduction using spatial and spectral regularized local discriminant embedding for hyperspectral image classifica- tion,” IEEE Trans. Geosci. Remote Sens., vol. 53, no. 2, pp. 1082-1095, Feb. 2015, doi: https://doi.org/10.1109/TGRS.2014.2333539
R. Hang, Q. Liu, H. Song, and Y. Sun, “Matrix-based discriminant subspace ensem- ble for hyperspectral image spatial-spectral feature fusion,” IEEE Trans. Geosci. Remote Sens., vol. 54, no. 2, pp. 783-794, Feb. 2016, doi: https://doi.org/10.1109/TGRS.2015.2465899
B. N. Soomro, N. A. jaffar, S. bhatti, and L. A. thebo, “A unique spectral spatial bayesian framework via elastic net regression for the classification of hyperspectral images”,SindhUniv. Res. Jour. (Sci. Ser.), vol. 51, no. 3, pp. 555-564, 2019, doi:
http://doi.org/10.26692/sujo/2019.03.87
M. Xu, H. Fang, P. Lv, L. Cui, S. Zhang, and B. Zhou, “D-stc: deep learning with spa- tio-temporal constraints for train drivers detection from videos,” Pattern Recog. Letters., vol. 119, pp. 222-228, Mar. 2019, doi: https://doi.org/10.1016/j.patrec.2017.09.040
Copyright (c) 2022 Zohaib Ahmad, Bushra Naz, Sara Ali, Zakir Shaikh
This work is licensed under a Creative Commons Attribution 4.0 International License.
UMT-AIR follow an open-access publishing policy and full text of all published articles is available free, immediately upon publication of an issue. The journal’s contents are published and distributed under the terms of the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. Thus, the work submitted to the journal implies that it is original, unpublished work of the authors (neither published previously nor accepted/under consideration for publication elsewhere). On acceptance of a manuscript for publication, a corresponding author on the behalf of all co-authors of the manuscript will sign and submit a completed the Copyright and Author Consent Form.
