Volume 15, Issue 2 (3-2023)                   itrc 2023, 15(2): 19-28 | Back to browse issues page


XML Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Farajzadeh A, Imani M, Mohammadi S. Hyperspectral Image Super Resolution Using Anomaly Weighted Gabor Based CNN. itrc 2023; 15 (2) : 3
URL: http://journal.itrc.ac.ir/article-1-560-en.html
1- Department of Electrical Engineering University of Zanjan Zanjan, Iran
2- Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran, Iran , maryam.imani@modares.ac.ir
3- Department of Electrical Engineering University of Zanjan Zanjan, Iran
Abstract:   (1328 Views)
Hyperspectral images have high spectral resolution. But, due to the tradeoff between spectral and spatial resolution and various hardware constraints, imaging a hyperspectral image with high spatial resolution is not practical. Hyperspectral super resolution is a soft approach to solve this challenge. Recently, deep learning based methods such as convolutional neural network (CNN) show great success in this field. But, the contextual details in object boundaries and anomalies present in the scene are not well addressed. To this end, a new CNN based framework is proposed for hyperspectral image super resolution in this work. To improve ability of the convolutional blocks in simultaneous extraction of spectral and spatial characteristics, the weighted Gabor features are concatenated in output of the defined convolutional blocks. To extract more details containing anomalous targets present in the scene, the anomaly scores of pixels are calculated and used for weighting the Gabor features. The experiments on three real hyperspectral images acquired by AVIRIS and ROSIS sensors show superior performance of the proposed framework compared to several state-of-the-art methods based on CNN and residual networks. In addition to common super resolution metrics such as SAM and ERGAS, the efficiency of different methods are evaluated according to the classification accuracy metrics such as overall accuracy and kappa coefficient. The overall classification accuracy is increased from 70.39 to 88.23 in Indian dataset, from 86.07 to 96.20 in Pavia University dataset, and from 95.82 to 99.12 in Pavia center dataset.
Article number: 3
Full-Text [PDF 1414 kb]   (632 Downloads)    
Type of Study: Research | Subject: Information Technology

References
1. [1] Banerjee, B. P., Raval, S., Cullen, P. J. 2020. UAV- hyperspectral imaging of spectrally complex environments, International Journal of Remote Sensing,41 (11): 4136-4159. [DOI:10.1080/01431161.2020.1714771]
2. [2] He, W., Chen, Y., Yokoya, N., Li, C., Zhao, Q. 2022.Hyperspectral super-resolution via coupled tensor ring factorization, Pattern Recognition, 122 (108280). [DOI:10.1016/j.patcog.2021.108280]
3. [3] Vivone, G. 2023. Multispectral and hyperspectral image fusion in remote sensing: A survey, Information Fusion,89: 405-417. [DOI:10.1016/j.inffus.2022.08.032]
4. [4] Imani, M., Ghassemian, H. 2020. An overview on Spectral and Spatial Information Fusion for Hyperspectral Image Classification: Current Trends and Challenges, Information Fusion, 59: 59-83. [DOI:10.1016/j.inffus.2020.01.007]
5. [5] Kanatsoulis, C. I., Fu, X., Sidiropoulos, N. D., Ma, W. 2018. Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach," in IEEE Transactions on Signal Processing, 66 (24): 6503-6517. [DOI:10.1109/TSP.2018.2876362]
6. [6] Simsek, M., Polat, E. 2021. Performance evaluation of pan-sharpening and dictionary learning methods for sparse representation of hyperspectral super-resolution. SIViP 15, 1099-1106. [DOI:10.1007/s11760-020-01836-8]
7. [7] Tang, S., Xiao, L., Huang, W., Liu, P., Wu, H. 2015. Pan-sharpening using 2D CCA, Remote Sensing Letters, 6(5): 341-350. [DOI:10.1080/2150704X.2015.1034882]
8. [8] Dixit, A., Agarwal, S. 2020. Super-resolution mapping of hyperspectral data using Artificial Neural Network and wavelet, Remote Sensing Applications: Society and Environment, 20 (100374). [DOI:10.1016/j.rsase.2020.100374]
9. [9] Dhara, S. K., Sen, D. 2019. Across-scale process similarity based interpolation for image super-resolution, Applied Soft Computing, 81 (105508). [DOI:10.1016/j.asoc.2019.105508]
10. [10] Fernandez-Beltran, R., Latorre-Carmona, P., Pla, F.2017. Latent topic-based super-resolution for remote sensing, Remote Sensing Letters, 8 (6): 498-507. [DOI:10.1080/2150704X.2017.1287974]
11. [11] Lee, M. C., Chiu, S. Y., Chang, J. W. 2017. A Deep Convolutional Neural Network based Chinese Menu Recognition App, Information Processing Letters, 128:14-20. [DOI:10.1016/j.ipl.2017.07.010]
12. [12] Arun, P.V., Buddhiraju, K.M., Porwal, A., Chanussot, J. 2020. CNN based spectral super-resolution of remote sensing images, Signal Processing, 169 (107394). [DOI:10.1016/j.sigpro.2019.107394]
13. [13] Wang, X., Ma, J., Jiang, J., Zhang, X.-P. 2021. Dilated projection correction network based on autoencoder for hyperspectral image super-resolution, Neural Networks. [DOI:10.1016/j.neunet.2021.11.014] [PMID]
14. [14] Hao, S., Wang, W., Ye, Y., Li, E., Bruzzone, L. 2018. A Deep Network Architecture for Super-Resolution- Aided Hyperspectral Image Classification With Classwise Loss, IEEE Transactions on Geoscience and Remote Sensing, 56 (8): 4650-4663. [DOI:10.1109/TGRS.2018.2832228]
15. [15] Wang, L., Bi, T., Shi, Y. 2020. A Frequency-Separated 3D-CNN for Hyperspectral Image Super-Resolution, IEEE Access, 8: 86367-86379. [DOI:10.1109/ACCESS.2020.2992862]
16. [16] Dong, W., Zhou, C., Wu, F., Wu, J., Shi, G., Li, X. 2021. Model-Guided Deep Hyperspectral Image Super-Volume 15- Number 2 - 2023 (19 -28) 27 Resolution," in IEEE Transactions on Image Processing, 30: 5754-5768. [DOI:10.1109/TIP.2021.3078058] [PMID]
17. [17] Hammouche, R., Attia, A., Akhrouf, S., Akhtar, Z.2022. Gabor filter bank with deep autoencoder based face recognition system, Expert Systems with Applications, 197 (116743). [DOI:10.1016/j.eswa.2022.116743]
18. [18] Ghassemi, M., Ghassemian, H., Imani, M. 2021.Hyperspectral Image Classification by Optimizing Convolutional Neural Networks based on Information Theory and 3D-Gabor Filters, International Journal of Remote Sensing, 42 (11): 4383-4413. [DOI:10.1080/01431161.2021.1892854]
19. [19] Paoletti, M.E., Haut, J.M., Plaza, J., Plaza, A. 2019. Deep learning classifiers for hyperspectral imaging: A review, ISPRS Journal of Photogrammetry and Remote Sensing, 158: 279-317. [DOI:10.1016/j.isprsjprs.2019.09.006]
20. [20] Boggavarapu, L.N. P. K., Manoharan, P. 2020. A new framework for hyperspectral image classification using Gabor embedded patch based convolution neural network, Infrared Physics & Technology, 110 (103455). [DOI:10.1016/j.infrared.2020.103455]
21. [21] Imani, M. 2017. RX Anomaly Detector with Rectified Background, IEEE Geoscience and Remote Sensing Letters, 14 (8): 1313-1317. [DOI:10.1109/LGRS.2017.2710618]
22. [22] Han, X. -H., Chen, Y. -W. 2019. Deep Residual Network of Spectral and Spatial Fusion for Hyperspectral Image Super-Resolution, 2019 IEEE Fifth International Conference on Multimedia Big Data (BigMM), pp. 266-270. [DOI:10.1109/BigMM.2019.00-13]
23. [23] Liu, D., Li, J., Yuan, Q. 2021. A Spectral Grouping and Attention-Driven Residual Dense Network for Hyperspectral Image Super-Resolution, IEEE Transactions on Geoscience and Remote Sensing, 59(9): 7711-7725. [DOI:10.1109/TGRS.2021.3049875]
24. [24] Vassilo, K., Taha, T., Mehmood, A. 2021. Infrared Image Super Resolution with Deep Neural Networks, 2021 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), pp. 1-5. [DOI:10.1109/WHISPERS52202.2021.9484045]
25. [25] Zhu, Z., Hou, J., Chen, J., Zeng, H., Zhou, J. 2021. Hyperspectral Image Super-Resolution via Deep Progressive Zero-Centric Residual Learning, IEEE Transactions on Image Processing, 30: 1423-1438. [DOI:10.1109/TIP.2020.3044214] [PMID]
26. [26] Yan, Q., Zhang, J., Feng, J. 2020. Spectral-Spatial Classification of Hyperspectral Image Using PCA and Gabor Filtering, IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, pp. 513-516. [DOI:10.1109/IGARSS39084.2020.9324555]
27. [27] Imani, M. 2018. Anomaly detection from hyperspectral images using clustering based feature reduction, Journal of the Indian Society of Remote Sensing, 46(9):1389-1397. [DOI:10.1007/s12524-018-0784-0]
28. [28] Imani, M. 2018. 3D Gabor Based Hyperspectral Anomaly Detection, AUT Journal of Modeling and Simulation, 50 (2): 189-194.
29. [29] Chang, C., Linin, C. 2008. LIBSVM-A Library for Support Vector Machines, [Online]. Available:http://www.csie.ntu.edu.tw/~cjlin/libsvm.

Add your comments about this article : Your username or Email:
CAPTCHA

Send email to the article author


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.