USAGE OF INTELLIGENT METHODS FOR MULTISPECTRAL DATA PROCESSING IN THE FIELD OF ENVIRONMENTAL MONITORING
Article Sidebar
Main Article Content
Abstract
The subject of study in the article is artificial intelligence methods that can be used for recognition of specific areas of the earth's surface in multispectral images provided by Earth remote sensing systems (ERS). The goal is to automate data analysis for recognizing areas affected by fire on multispectral remote sensing images. The task is to study and formulate a method for processing multispectral data, which makes it possible to automate the process of operational recognition of areas of burned-out areas in images, for the development of an eco-monitoring software system using artificial intelligence tools such as deep learning and neural networks. As a result of the analysis of modern methods of processing multispectral data, an investigation of the supervised learning strategy was chosen. The choice of the described method for solving an applied problem is based on the high flexibility of these method, as well as, provided that there is a sufficient amount of used training input data and correct training strategies, the possibility of analyzing heterogeneous multispectral data with ensuring high accuracy of results for each individual sample. Conclusions: the application of methodologies for intelligent processing of multispectral images has been investigated and substantiated. The theoretical foundations of the construction of neural networks are considered, the applied area of application is selected. An architectural model of a software product is analyzed and proposed, taking into account its scalability, the model of software system is developed and the results of its work are shown. The obtained results show the efficiency of proposed system and prospects of the proposed algorithms, which is a reason for further research and improvement of the used algorithms, with their possible use in industrial and enterprise eco-monitoring systems.
Article Details
References
Kvochka M. and Podorozhniak A. (2020), “Intelligent ecomonitoring solutions” [Vykorystannia zasobiv hlybynnoho navchannia u haluzi ekomonitorynhu], Informatization problems, 7th International Conference on: November 13-15, 2020, Cherkasy-Kharkiv-Baku-Balsko-Biala: Vol. 2., p. 51, available at: http://repository.kpi.kharkov.ua/bitstream/KhPI-Press/42754/1/Conference_NTU_KhPI_2019_Problemy_informatyzatsii_Ch_2.pdf.
Kvochka M. and Podorozhniak A. (2020), “Intelligent ecomonitoring solutions” [Intelektualni rishennia u haluzi ekomonitorynhu], Modern development directions of information and communication technologies and controls, 10th International Conference on: April 9-10, 2020, Baku-Kharkiv-Žilina: Vol. 1., p. 97, available at: http://repository.kpi.kharkov.ua/bitstream/KhPI-Press/53485/1/Podorozhniak_Intelektualni_2020.pdf.
Ramachandran B., Justice C.O. and Abrams M.J. (2011), Land Remote Sensing and Global Environmental Change, Springer, 873 p. DOI: https://doi.org/10.1007/978-1-4419-6749-7.
Chang-I C. (2013), Hyperspectral Data Processing: Algorithm Design and Analysis, John Wiley&Sons, 1st edition, 1164 p. DOI: https://doi.org/10.1002/9781118269787
Nahar, K. (2012), "Artificial neural network", COMPUSOFT, An international journal of advanced computer technology, Vol. 1, No. 2, pp. 25-27, available at: https://ijact.in/index.php/ijact/article/view/421/.
Dong H., Li T., Leng J., Kong L. and Bai G. (2017), “GCN: GPU-based Cube CNN Framework for Hyperspectral Image Classification”, IEEE 46th International Conference on Parallel Processing (ICPP), DOI: https://doi.org/10.1109/ICPP.2017.13
Podorozhniak A., Kvochka M. (2021), “Multispectral images processing using systems on chips”, Modern development directions of information and communication technologies and controls, 11th International Conference on: April 8-9, 2021, Baku-Kharkiv-Kyiv-Žilina: Vol. 2., p. 31, available at: http://repository.kpi.kharkov.ua/bitstream/KhPI-Press/52974/1/Podorozhniak_Multispectral_images_2021.pdf.
Vargas R., Mosavi A. and Ruiz R. (2018), "Deep learning: a review", Advances in Intelligent Systems and Computing, DOI: https://doi.org/10.20944/preprints201810.0218.v1.
Liubchenko N., Podorozhniak A. and Bondarchuk V. (2017), "Neural network method of intellectual processing of multispectral images", Advanced information System, Vol. 1, No. 2, pp. 39-44, DOI: https://doi.org/10.20998/2522-9052.2017.2.07.
Podorozhniak A., Lubchenko N., Balenko O. and Zhuikov D. (2018), "Neural network approach for multispectral image processing". Advanced Trends in Radioelecrtronics, Telecommunications and Computer Engineering (TCSET-2018), 14th International Conference on: IEEE, pp. 978-981, available at: http://dx.doi.org/10.1109/TCSET.2018.8336357.
Pinto M.M. (2021), “Mapping burned areas from space with Artificial Intelligence”, available at: https://medium.com/@mnpinto/mapping-burned-areas-from-space-with-artificial-intelligence-3657bdb97a9d.
Patterson J. and Gibson A. (2017), Deep Learning: A Practitioner's Approach, O'Reilly Media, 538 p. ISBN: 9781491914250.
Hui J. (2017), "Understanding Matrix capsules with EM Routing (Based on Hinton's Capsule Networks)", available at: https://jhui.github.io/2017/11/14/Matrix-Capsules-with-EM-routing-Capsule-Network/.
Hlavcheva D. and Yaloveha V. (2018), "Capsule neural networks", Control, Navigation and Communication Systems, Vol. 5, No. 51, pp. 132-135, DOI: https://doi.org/10.26906/SUNZ.2018.5.132.
Pinto M. M., Libonati R., Trigo R. M., Trigo I. F. & DaCamara C. C. (2020), "A deep learning approach for mapping and dating burned areas using temporal sequences of satellite images", ISPRS Journal of Photogrammetry and Remote Sensing, 160, 260–274, DOI: https://doi.org/10.1016/j.isprsjprs.2019.12.014.
Bengio, Y. (2009), "Learning deep architectures for AI", Foundations and trends in Machine Learning, Vol. 2, No. 1, pp. 1-127, DOI: https://doi.org/10.1561/2200000006.
Johnston B. and Mathur I. (2019), Applied Supervised Learning with Python, Packt Publishing, 2019, 404 p. ISBN: 9781789954920.
Pinto M. M. (2020), BA-Net: A deep learning approach for mapping and dating burned areas using temporal sequences of satellite images, available at: https://github.com/mnpinto/banet#train-the-model-from-scratch.
Mosavi A. and Varkonyi-Koczy A. R. (2017), "Integration of machine learning and optimization for robot learning", Recent Global Research and Education: Technological Challenges: Springer, pp. 349-355, DOI: https://doi.org/10.1007/978-3-319-46490-9_47.
McKinney W. (2017), Python for Data Analysis, 2nd Edition, O'Reilly Media, 544 p. ISBN: 9781491957660.