Leveraging Deep Hierarchies in CNNs for Enhanced Satellite Image Classification
Keywords:
Multi-level CNN, Satellite imagery, Remote Sensing, Artificial Intelligence, Deep learning, Classification.Abstract
Satellite imagery has been transforming our understanding and prediction of global economic activity with evolution in hardware and in much less cost for rocket launching enabling near real time and high resolution coverage across the earth. It is impractical to analyse petabytes of satellite imagery manually, requiring automated solutions with higher accuracy and prediction speed, essential for latency sensitive industrial applications. Enhancement in recognition model design, training and complexity regularization, along with a Multi-Level Convolutional neural network architecture optimized for satellite imagery, the proposed model has made it possible to deliver fivefold improvement in training time and rapid prediction of 20 classes which is necessary for real-time applications. We have substantiated the proficiency through reviewing algorithmic trading environments and release a proprietary annotated satellite imagery dataset for further research. Satellite imagery play influential roles in disaster response, law enforcement, and environmental monitoring. Demanding automated object identification because of its coverage across the globe's geography. The Multi-Level Convolutional Neural Network, as proposed, underwent training with a training dataset comprising 7000 images (350 images for each of the classes), achieving a training accuracy of 98.14%. Upon evaluation on a separate test dataset consisting of 3000 images (150 images per class), the model demonstrated an overall accuracy of 95%. Moreover, each class is predicted with an accuracy of 99% when tested individually. The whole implementation is carried out in Python using Keras, TensorFlow, and Gocolab with GPU and High RAM.
Downloads
References
Almisreb, A.A., Jamil, N. and Din, N.Md., 2018. Utilizing AlexNet deep transfer learning for ear recognition. Fourth International Conference on Information Retrieval and Knowledge Management (CAMP). doi: 10.1109/INFRKM.2018.8464769.
Birk, R., Stanley, T., Snyder, G., Henning, T., Fladeland, M. and Policelli, F., 2003.Government programs for research and operational uses of commercial remote sensing data. Remote Sensing of Environ., vol. 88, no.1-2, pp.3-16. doi:10.1016/j.rse.2003.07.007.
Bezdek,C., Ehrllich,R. and Full,W., 2018. FCM:Fuzzy c-means clustering Algorithm. Computers and Geosciences, vol.2,pp.191-203.
Campell, J., 1996. Introduction to Remote Sensing, 2nd edition, London, U.K.: Taylor & Francis.
He, K., Zhang, X., Ren, S. and Sun, J.,2015. Deep residual learning for image recognition, Computer Vision and Pattern Recoginition(CVPR).doi: https://doi.org/10.48550/arXiv.1512.03385.
Huang, G., Liu, Z., Maaten, L. and Weinberger,K.Q., 2017. Dense connected convolutional neural networks, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). doi: https://doi.org/10.48550/arXiv.1608.06993
Hussain, M., Bird, J.J. and Faria, D.R.,2018. A study on CNN transfer learning for image classification. 18th Annual UK Workshop on Computational Intelligence (UKCI), Nottingham.
Krizhevsky,A., Sutskever,I., and Hinton,G., 2012. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25 (NIPS 2012).
Kwan, H.K. and Lee, C.K., 1993. A neural network approach to pulse radar detection. IEEE Trans. Aerosp. Electron. Syst. vol. 29(1), pp.9–21. doi: https://doi.org/10.1109/7.249109
LeCun, Y., Bengio, Y., and Hinton, G., 2015.Deep learning. Nature, vol. 521, pp. 436-444. doi: https://doi.org/10.1038/nature14539.
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W. and Jackel, L. D.,1989. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation, vol. 1(4), pp.541-551. doi: 10.1162/neco.1989.1.4.541.
Landgrebe, D.A., 2003.Signal Theory Methods in Multispectral Remote Sensing. NJ, Hoboken: Wiley.
Liang, Y., Monteiro, S and Saber, E., 2016.Transfer learning for highresolution aerial image classification. IEEE Workshop Applied Imagery Pattern Recognition (AIPR), doi: arXiv:1510.00098v2
Nascimento, I., Flavio,M., Marcus, D., Andrey, S. and Aldebaro, K.,(2018). Deep learning in RAT and modulation classification with a new radio signals dataset, Simpósio brasileiro de telecomunicações e processamento de sinais - sbrt, 16–19 de setembro de. doi:10.14209/sbrt.2018.144.
Patil et al.,2018. Object detection in military and space image by deep learning with a convolutional neural network", Int. J. Comput. Sci. Eng., vol. 6(11), pp.363–368.
Pouyanfar, S., Sadiq, S., Yan, Y., Tian, H., Tao, Y., Reyes, M. P. and Iyengar, S. S.,2018. A survey on deep learning: Algorithms, techniques, and applications. ACM Computing Surveys (CSUR) Vol. 51(5): 92, pp. 1–36. doi: https://doi.org/10.1145/3234150.
Pahuja, D. and Jain, S.,2022 An Automatic Detection of Military Weapons Using Multi-Level CNN Architecture.10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Noida, India, pp. 1-4, doi: 10.1109/ICRITO56286.2022.9964878.
Pritt, M. and Chern, G.,2020. Satellite Image Classification with Deep Learning. Computer Vision and Pattern Recognition(CPVR), doi: https://doi.org/10.48550/arXiv.2010.06497.
Rai, A.K., Mandal, N., Singh, A. and Singh, K.K., 2020. Landsat 8 OLI Satellite Image Classification using Convolutional Neural Network. Procedia Computer Science vol. 167, pp.987-993. doi: https://doi.org/10.1016/j.procs.2020.03.398.
Remjee, S., Ju, S., Yang, D., Liu,X. and Gamal, A.E. and Eldar, Y.C., 2019. Fast deep learning for automatic modulation classification. Electrical Engineering and Systems Science: Signal Processing. doi: https://doi.org/10.48550/arXiv.1901.05850.
Schowengerdt, R., 1997. Remote Sensing, Models and Methods, for Image Processing, 2nd Edition, Academic Press, Cambridge.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A, 2014. Going deeper with convolutions. CoRR, abs/1409.4842.
Szegedy,C., Vanhoucke,V., Loffe,L., Shlens,J. and Wojna, J.,2015.Rethinking the Inception Architecture for Computer Vision. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). doi: https://doi.org/10.48550/arXiv.1512.00567.
Simonyan, K. and Zisserman, A., 2015. Very deep convolutional networks for large-scale image recoginition(ICLR), Computer Vision and Pattern Recoginition(CVPR).
doi: https://doi.org/10.48550/arXiv.1409.1556.
Singh, D. and Garzon, P.,2018. Using Convolutional Neural Networks and Transfer Learning to Perform Yelp Restaurant Photo Classification.
Smith, P. and Chen, C.,2018. Transfer learning with deep CNNs for gender recognition and age estimation. IEEE international conference on Big Data. doi: https://doi.org/10.1109/BigData.2018.862189.
Signoroni, A., Savardi, M., Baronio, A. and Benini, S.,2019. Deep learning meets hyperspectral image analysis: a multidisciplinary review. J. Imaging 5, 52, doi: https://doi.org/10.3390/jimaging5050052
Talo, M., Baloglu,U.B., Yıldırım,O. and Acharya,U.R., 2018. Application of deep transfer learning for automated brain abnormality classification using MR images. Cognitive Systems Research, vol.54, pp.176–188.doi: https://doi.org/10.1016/j.cogsys.2018.12.007
Wang, S.H., Xie, S., Chen, X., Guttery, D.S., Tang, C., Sun, J. and Zhang, Y.D., 2019. Alcoholism Identification Based on an AlexNet Transfer Learning Model, Front Psychiatry. doi: 10.3389/fpsyt.2019.00205. PMID: 31031657; PMCID: PMC6470295.
Wu, Y. and Ji, Q., 2016. Constrained deep transfer feature learning and its applications. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5101–5109. doi: https://doi.org/10.48550/arXiv.1709.08128
Yang, Z., Yu, W., Liang, P. Guo, H., Xia, L., Zhang, F., Ma, Y., and Ma J, 2019. Deep transfer learning for military object recognition under small training set condition. Neural Comput Appl, vol. 31(10), pp.6469–6478. doi: https://doi.org/10.1007/s00521-018-3468-3
Zhang, C., Pan, X., Li, H., Gardiner, A., Sargent, I., Hare, J. and Atkinson, P.,2018. A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS Journal of Photogrammetry and Remote Sensing vol. 140, pp.133-144. doi: https://doi.org/10.1016/j.isprsjprs.2017.07.014.
Zhao, W., Gou, Z., Yue, J , Zhang, X. and Luo, L, 2015.On combining multiscale deep learning features for the classification of hyperspectral remote sensing imagery. Int. Journal of Remote Sensing. vol.36 pp., 3368–3379 doi: 10.1080/2150704X.2015.1062157.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
