PERFORMANCE COMPARISON OF U-NET AND LINKNET WITH DIFFERENT ENCODERS FOR REFORESTATION DETECTION
Article Sidebar
Main Article Content
Abstract
The subject of study is analysis of performance of artificial intelligence systems with different architectures for reforestation detection. The goal is to implement, train and evaluate system with different models for deforestation and reforestation detection. The tasks are to study problems and potential solutions in forestry for reforestation detection and present own solution. As part of model comparison, results are presented for different artificial neural network architectures with different encoders. For training and testing purpose custom dataset was created, which includes different areas of territory of Ukraine within different timestamps. Main research methods are literature analysis, experiment and case study. As a result of analysis of modern artificial intelligence methods, machine learning, deep learning and convolutional neural networks, high-precision algorithms U-Net and LinkNet were chosen for system implementation. Conclusions. The studied problem was stated formally and broken down in smaller steps; possible solutions were studied and proposed solution was described in details. Necessary mathematical background for analysis of the performance was provided. As part of the development, accurate deforestation/reforestation module was created. All analysis results were listed and a comparison of the studied algorithms was presented.
Article Details
References
Devis, T., Konrad, S., Begüm, D., Gustau, C-V., Xiao, Z., Mrinalin,i K., Sašo, D., van Rijn, J., Holge,r H., Frate, F. D., Mihai, D., Jorge-Arnulfo, Q-R., Volker, M., Bertrand, S. and Rochelle, S. (2023), “Artificial intelligence to advance Earth observation: a perspective“, arXiv: 2305.08413v1 [cs.CV], 15 May 2023, doi: https://doi.org/10.48550/arXiv.2305.08413
Imangholiloo, M., Luoma, V., Holopainen, M., Vastaranta, M., Mäkeläinen, A., Koivumäki, N., Honkavaara, E. and Khoramshahi, E. (2023), “A New Approach for Feeding Multispectral Imagery into Convolutional Neural Networks Improved Classification of Seedlings”, Remote Sensing, 2023, Vol. 15 (21), 5233, doi: https://doi.org/10.3390/rs15215233
Prapas, I., Ioannis, B. N., Kondylatos, S., Michail, D., Camps-Valls, G. and Papoutsis, I. (2023), "TeleViT: Teleconnection-driven Transformers Improve Subseasonal to Seasonal Wildfire Forecasting", arXiv: 2306.10940v2 [cs.CV], 2 Aug 2023, doi: https://doi.org/10.48550/arXiv.2306.10940
(2022), Global Forest Watch, available at: https://www.globalforestwatch.org/dashboards/global/
(2023), Public report of the head of the State Forest Resources Agency of Ukraine for 2022, State Agency of Forest Resources of Ukraine, 35 p., available at: https://forest.gov.ua/storage/app/sites/8/publich_zvit/publichnii-zvit-za-2022.pdf
Vaghela, H. P., and Alagu, R. R. A. (2024), “Automatic Identification of Tree Species from Sentinel-2A Images Using Band Combinations and Deep Learning”, IEEE Geoscience and Remote Sensing Letters, 2024, vol. 21, pp. 1-5. doi: https://doi.org/10.1109/LGRS.2024.3354814
Podorozhniak, A., Liubchenko, N. and Onishchenko, D. (2023), "Forest Recovery Detection Based on U-Net and LinkNet," Proceedings of 2023 IEEE 4th KhPI Week on Advanced Technology (KhPIWeek), Kharkiv, Ukraine, 02-06 October 2023, pp. 1–4, doi: https://doi.org/10.1109/KhPIWeek61412.2023.10312869
Csurka, G., Volpi, R. and Chidlovskii, B. (2023), "Semantic Image Segmentation: Two Decades of Research", arXiv: 2302.06378 [cs.CV], 13 Feb 2023, doi: https://doi.org/10.48550/arXiv.2302.06378
Podorozhniak, A., Liubchenko, N., Sobol, M. and Onishchenko, D. (2023), “Usage of Mask R-CNN for automatic license plate recognition”, Advanced Information Systems, 2023, Vol. 7, No. 1, pp. 54–58, doi: https://doi.org/10.20998/2522-9052.2023.1.09
(2023), “Landsat-8”, USGS: Landsat missions, available at: https://www.usgs.gov/landsat-missions/landsat-8
(2023), “Sentinel-2 mission guide”, Sentinel Online, available at: https://sentinel.esa.int/web/sentinel/missions/sentinel-2
Radeloff, V. C., Roy, D. P., Wulder, M. A., Anderson, M., Cook, B., Crawford, C. J., Friedl, M., Gao F., Gorelick, N., Hansen, M., Healey, S., Hostert, P., Hulley, G., Huntington, J. L., Johnson, C., Lyapustin, A., Lymburner, L., Pahlevan, N., Pekel, J.-F., C. E., Zhang H. K. and Zhu, Z. (2023), “Need and vision for global medium-resolution Landsat and Sentinel-2 data products”, Remote Sensing of Environment, 2023, 300, 113918, doi: https://doi.org/10.1016/j.rse.2023.113918
(2023), United States Geological Survey, available at: https://www.usgs.gov
Diaz, E. (2017), “Online deforestation detection”, arXiv: 1704.00829 [stat.AP], 3 Apr 2017, doi:
https://doi.org/10.48550/arXiv.1704.00829
Yaloveha, V., Hlavcheva, D. and Podorozhniak, A. (2021), “Spectral Indexes Evaluation for Satellite Images Classification using CNN”, Journal of Information and Organizational Sciences, 2021, Vol. 45, No. 2, pp. 435–449, doi: https://doi.org/10.31341/jios.45.2.5
Liu, X., Deng, Z. and Yang, Y. (2019), "Recent progress in semantic image segmentation", Artificial Intelligence Review, Vol. 52, pp. 1089–1106, doi: https://doi.org/10.1007/s10462-018-9641-3
He, W., Jamonnak, S., Gou, L. and Ren, L. (2023), "CLIP-S: Language-Guided Self-Supervised Semantic Segmentation", arXiv: 2305.01040 [cs.CV], 1 May 2023, doi: https://doi.org/10.48550/arXiv.2305.01040
Yaloveha, V., Podorozhniak, A. and Kuchuk, H. (2022), “Convolutional neural network hyperparameter optimization applied to land cover classification”, Radioelectronic and Computer Systems, No. 1(2022), pp. 115–128, doi: https://doi.org/10.32620/reks.2022.1.09
Parzhin, Y., Kosenko, V., Podorozhniak, A., Malyeyeva, O. and Timofeyev, V. (2020), “Detector neural network vs connectionist ANNs”, Neurocomputing, 2020, 414, pp. 191–203, doi: https://doi.org/10.1016/j.neucom.2020.07.025
O'Shea, K. and Nash, R. (2015), “An Introduction to Convolutional Neural Networks”, arXiv: 1511.08458 [cs.NE], 26 Nov 2015, doi: https://doi.org/10.48550/arXiv.1511.08458
Kovalenko, A. and Kuchuk, H. (2022), “Methods to Manage Data in Self-healing Systems”, Studies in Systems, Decision and Control, Vol. 425, pp. 113–171, doi: https://doi.org/10.1007/978-3-030-96546-4_3
Volovyk, A. (2023), “Synthesis of quasi-optimal fast filters by the least square criterion”, Advanced Information Systems, 2023, Vol. 7, No. 2, pp. 21–27. doi: https://doi.org/10.20998/2522-9052.2023.2.04
Bank, D., Koenigstein, N. and Giryes, R. (2020), "Autoencoders", arXiv: 2003.05991 [cs.LG], 12 Mar 2020, doi: https://doi.org/10.48550/arXiv.2003.05991
Ronneberger, O., Fischer, P. and Brox, T. (2015), "U-Net: Convolutional Networks for Biomedical Image Segmentation", arXiv: 1505.04597 [cs.CV], 18 May 2015, doi: https://doi.org/10.48550/arXiv.1505.04597
Chaurasia, A. and Culurciello, E. (2017), "LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation", Proceedings of 2017 IEEE Visual Communications and Image Processing (VCIP), St. Petersburg, FL, USA, 10–13 December 2017, doi: https://doi.org/10.1109/VCIP.2017.8305148
Simonyan, K. and Zisserman, A. (2014), "Very Deep Convolutional Networks for Large-Scale Image Recognition", arXiv: 1409.1556 [cs.CV], 4 Sep 2014, doi: https://doi.org/10.48550/arXiv.1409.1556
He, K., Zhang, X., Ren, S. and Sun, J. (2015), "Deep Residual Learning for Image Recognition", arXiv: 1512.03385 [cs.CV], 10 Dec 2015, doi: https://doi.org/10.48550/arXiv.1512.03385
Tan, M. and Le, Q. V. (2019), "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks", arXiv: 1905.11946 [cs.LG], 28 May 2019, doi: https://doi.org/10.48550/arXiv.1905.11946
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. and Chen, L.-C. (2018), "MobileNetV2: Inverted Residuals and Linear Bottlenecks", arXiv: 1801.04381 [cs.CV], 13 Jan 2018, doi: https://doi.org/10.48550/arXiv.1801.04381
Gavrylenko, S., Vladislav, Z. and Khatsko, N. (2023), "Methods for Improving the Quality of Classification on Imbalanced Data," Proceedings of 2023 IEEE 4th KhPI Week on Advanced Technology (KhPIWeek), Kharkiv, Ukraine, 02–06 October 2023, pp. 1–5, doi: https://doi.org/10.1109/KhPIWeek61412.2023.10312879