Novel Ensemble-Based Deep Learning Model for Remote Sensing Images Classification
Keywords:
Deep learning, Particle swarm optimization, Hyper-parameters, Remote sensing imagesAbstract
Scene classification from remote
sensing images is still defined as an ill-posed
problem. Deep learning models outperform the
competitive techniques but suffer from various
issues. These issues are it has been observed that
the majority of existing deep learning models such
as deep convolutional neural networks, etc. suffer
from premature convergence issues. It limits the
performance of scene classification. The tuning of
the hyper-parameters of deep learning models is
still a challenging issue, therefore, automating the
tuning of these parameters is desirable. Deep
learning models may also suffer from overfitting
issues. To overcome these issues, a novel ensemblebased deep learning model is used to classify the
scenes in remote sensing images. To tune the
hyper-parameters of the proposed scene
classification model, the particle swarm
optimization algorithm is also used. The
comparative analysis show that the proposed
model outperforms the existing model.
References
G. Eason, B. Noble, and I. N. Sneddon, “On
certain integrals of Lipschitz-Hankel type
involving products of Bessel functions,” Phil.
Trans. Roy. Soc. London, vol. A247, pp. 529–
, April 1955. (references)
Q. Lu, X. Huang, J. Li and L. Zhang, "A Novel
MRF-Based Multifeature Fusion for
Classification of Remote Sensing Images," in
IEEE Geoscience and Remote Sensing Letters,
vol. 13, no. 4, pp. 515-519, April 2016.
doi:10.1109/LGRS.2016.2521418
S. Jia and J. Xian, "Multi-Feature-Based
Decision Fusion Framework for Hyperspectral
Imagery Classification," IGARSS 2018 - 2018
IEEE International Geoscience and Remote
Sensing Symposium, Valencia, 2018, pp. 5-8.
doi:10.1109/IGARSS.2018.8518355
O. Sen and H. YalimKeles, "Scene Recognition
with Deep Learning Methods Using Aerial
Images," 2019 27th Signal Processing and
Communications Applications Conference (SIU),
Sivas, Turkey, 2019, pp. 1-4. doi:
1109/SIU.2019.8806616
X. Xu, J. Li, X. Huang, M. Dalla Mura and A.
Plaza, "Multiple Morphological Component
Analysis Based Decomposition for Remote
Sensing Image Classification," in IEEE
Transactions on Geoscience and Remote
Sensing, vol. 54, no. 5, pp. 3083-
,May2016.doi:10.1109/TGRS.2015.251119
X. Xu, J. Li and M. Dalla Mura, "Remote
sensing image classification based on multiple
morphological component analysis," 2015 IEEE
International Geoscience and Remote Sensing
Symposium (IGARSS), Milan, 2015, pp. 2596-
doi:10.1109/IGARSS.2015.7326343
M. E. Paolettiet al., "Capsule Networks for
Hyperspectral Image Classification," in IEEE
Transactions on Geoscience and Remote
Sensing, vol. 57, no. 4, pp. 2145-2160, April
doi: 10.1109/TGRS.2018.2871782
J. Liu, Z. Wu, J. Li, L. Xiao, A. Plaza and J. A.
Benediktsson, "Spatial–Spectral Hyperspectral
Image Classification Using Random Multiscale
Representation," in IEEE Journal of Selected
Topics in Applied Earth Observations and
Remote Sensing, vol. 9, no. 9, pp. 4129-4141,
Sept. 2016.
doi: 10.1109/JSTARS.2016.2587678
T. Fukuda, M. Suzuki, G. Kurata, S. Thomas, J.
Cui, and B. Ramabhadran, “Efficient knowledge
distillation from an ensemble of teachers,” in
Interspeech 2017, 18th Annual Conference of the
International Speech Communication
Association, Stockholm, Sweden, August 20-24,
, F. Lacerda, Ed. ISCA, 2017, pp. 3697–
[Online]. Available: http://www.iscaspeech.org/archive/Interspeech
/abstracts/0614.html
G. Chen, X. Zhang, X. Tan, Y. Cheng, F. Dai,
K. Zhu, Y. Gong, and Q. Wang, “Training small
networks for scene classification of remote
sensing images via knowledge distillation,”
Remote. Sens., vol. 10, no. 5, p. 719, 2018.
[Online]. Available:
https://doi.org/10.3390/rs10050719
iJournals: International Journal of Software & Hardware Research in Engineering (IJSHRE)
ISSN-2347-4890
Volume 9 Issue 5 May 2021
© 2021, iJournals All Rights Reserved www.ijournals.in
© 2020, iJournals All Rights Reserved www.ijournals.in
Page 43
S. Pande, A. Banerjee, S. Kumar, B. Banerjee,
and S. Chaudhuri, “An adversarial approach to
discriminative modality distillation for remote
sensing image classification,” in 2019 IEEE/CVF
International Conference on Computer Vision
Workshop (ICCVW), 2019, pp. 4571– 4580.
R. Zhang, Z. Chen, S. Zhang, F. Song, G. Zhang,
Q. Zhou, and T. Lei, “Remote sensing image
scene classification with noisy label distillation,”
Remote. Sens., vol. 12, no. 15, p. 2376, 2020.
[Online]. Available:
https://doi.org/10.3390/rs12152376.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K.
and Fei-Fei, L., 2009. Imagenet: A large-scale
hierarchical image database. In: Proc. CVPR, pp.
–255.
Y. Liu, J. Li, A. Plaza, J. Bioucas-Dias, A.
Cuartero and P. G. Rodríguez, "Spectral
partitioning for hyperspectral remote sensing
image classification," 2014 IEEE Geoscience
and Remote Sensing Symposium, Quebec City,
QC, 2014, pp. 3434-3437.
doi: 10.1109/IGARSS.2014.6947220
J. Li, I. Dópido, P. Gamba and A. Plaza,
"Complementarity of Discriminative Classifiers
and Spectral Unmixing Techniques for the
Interpretation of Hyperspectral Images," in IEEE
Transactions on Geoscience and Remote
Sensing, vol. 53, no. 5, pp. 2899-2912, May
doi: 10.1109/TGRS.2014.2366513
M. Khodadadzadeh, J. Li, A. Plaza, H.
Ghassemian, J. M. Bioucas-Dias and X. Li,
"Spectral–Spatial Classification of Hyperspectral
Data Using Local and Global Probabilities for
Mixed Pixel Characterization," in IEEE
Transactions on Geoscience and Remote
Sensing, vol. 52, no. 10, pp. 6298-6314, Oct.
doi: 10.1109/TGRS.2013.2296031
J. Li et al., "Multiple Feature Learning for
Hyperspectral Image Classification," in IEEE
Transactions on Geoscience and Remote
Sensing, vol. 53, no. 3, pp. 1592-1606, March
doi: 10.1109/TGRS.2014.2345739
T. L. Ainsworth, J. Lee and Y. Wang,
"Robustness of model-based polsar
decomposition techniques," 2017 IEEE
International Geoscience and Remote Sensing
Symposium (IGARSS), Fort Worth, TX, 2017, pp.
-5286.
doi: 10.1109/IGARSS.2017.8128196
M. E. Paolettiet al., "Capsule Networks for
Hyperspectral Image Classification," in IEEE
Transactions on Geoscience and
Remote Sensing, vol. 57, no. 4, pp. 2145-2160,
April 2019. doi: 10.1109/TGRS.2018.2871782
J. Liu, Z. Wu, J. Li, L. Xiao, A. Plaza and J. A.
Benediktsson, "Spatial–Spectral Hyperspectral
Image Classification Using Random Multiscale
Representation," in IEEE Journal of Selected
Topics in Applied Earth Observations and
Remote Sensing, vol. 9, no. 9, pp. 4129-4141,
Sept. 2016.
doi: 10.1109/JSTARS.2016.2587678
Yang, Zhou, Xiao-dong Mu, and Feng-an Zhao.
"Scene classification of remote sensing image
based on deep network and multi-scale features
fusion." Optik 171 (2018): 287-293.
John E Ball, Derek T Anderson, and Chee Seng
Chan. Comprehensive survey of deep learning in
remote sensing: theories, tools, and challenges
for the community. Journal of Applied Remote
Sensing, 11(4):042609, 2017.
SudipanSaha, Francesca Bovolo, and Lorenzo
Bruzzone. Change detection in image time-series
using unsupervised lstm. IEEE Geoscience and
Remote Sensing Letters, 2020.
