Нейросетевая классификация гиперспектральных изображений растительности с формированием обучающей выборки на основе адаптивного вегетационного индекса
Автор: Фирсов Никита Александрович, Подлипнов Владимир Владимирович, Ивлиев Николай Александрович, Николаев Петр Петрович, Машков Сергей Владимирович, Ишкин Павел Александрович, Скиданов Роман Васильевич, Никоноров Артем Владимирович
Журнал: Компьютерная оптика @computer-optics
Рубрика: Обработка изображений, распознавание образов
Статья в выпуске: 6 т.45, 2021 года.
Бесплатный доступ
В настоящей работе предложен новый подход к классификации гиперспектральных изображений высокого разрешения в прикладной задаче определения типов сельскохозяйственной растительности. В качестве классификатора используется спектрально-пространственная сверточная нейронная сеть с компенсацией вариаций освещения. Для автоматизированного формирования обучающей выборки предложен алгоритм на основе адаптивного вегетационного индекса. Показана эффективность предложенного подхода в задаче классификации типов растительности по результатам съемок сельскохозяйственных угодий, выполненных сканирующей гиперспектральной камерой.
Гиперспектральные изображения, вегетационный индекс, сверточные нейронные сети, классификация растительности, спектрально-пространственная классификация гиперспектральных изображений, вегетационные индексы
Короткий адрес: https://sciup.org/140290288
IDR: 140290288 | DOI: 10.18287/2412-6179-CO-1038
Neural network-aided classification of hyperspectral vegetation images with a training sample generated using an adaptive vegetation index
In this paper, we propose an approach to the classification of high-resolution hyperspectral images in the applied problem of identification of vegetation types. A modified spectral-spatial convolutional neural network with compensation for illumination variations is used as a classifier. For generating a training dataset, an algorithm based on an adaptive vegetation index is proposed. The effectiveness of the proposed approach is shown on the basis of survey data of agricultural lands obtained from a compact hyperspectral camera developed in-house.
Список литературы Нейросетевая классификация гиперспектральных изображений растительности с формированием обучающей выборки на основе адаптивного вегетационного индекса
- Sharma, V. Hyperspectral CNN for image classification & band selection, with application to face recognition / V. Sharma, A. Diba, T. Tuytelaars, L. Van Gool [Electronical Resource]. - 2016. - URL: https://core.ac.uk/download/pdf/80805922.pdf (request date 29.07.2021).
- Zhang, J. Leaf area index estimation model for UAV image hyperspectral data based on wavelength variable selection and machine learning methods / J. Zhang, T. Cheng, W. Guo, X. Xu, H. Qiao, Y. Xie, X. Ma // Plant Methods. -2021. - Vol. 17, Issue 1. - P. 49-54.
- Siedliska, A. Identification of plant leaf phosphorus content at different growth stages based on hyperspectral reflectance / A. Siedliska, P. Baranowski, J. Pastuszka-Wozniak, M. Zubik, J. Krzyszczak // BMC Plant Biology. - 2021. -Vol. 21, Issue 1. - P. 28-32.
- Sahadevan, A.S. Extraction of spatial-spectral homogeneous patches and fractional abundances for field-scale agriculture monitoring using airborne hyperspectral images / A.S. Sahadevan // Computers and Electronics in Agriculture. - 2021. - Vol. 188. - 106325.
- Zhang, Y. Estimating the maize biomass by crop height and narrowband vegetation indices derived from UAV-based hyperspectral images / Y. Zhang, C. Xia, X. Zhang, X. Cheng, G. Feng, Y. Wang, Q. Gao // Ecological Indicators. - 2021. - Vol. 129. - 107985.
- La Rosa, L.E.C. Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data / L.E.C. La Rosa, C. Sothe, R.Q. Feitosa, C.M. de Almeida, M.B. Schimalski, D.A.B. Oliveira // IS-PRS Journal of Photogrammetry and Remote Sensing. -2021. - Vol. 179. - P. 35-49.
- Wang, L. Estimation of paddy rice nitrogen content and accumulation both at leaf and plant levels from UAV hyper-spectral imagery / L. Wang, S. Chen, D. Li, C. Wang, H. Jiang, Q. Zheng, Z. Peng // Remote Sensing. - 2021. -Vol. 13, Issue 15. - 2956.
- Vangi, E. The new hyperspectral satellite PRISMA: Imagery for forest types discrimination / E. Vangi, G. D'amico, S. Francini, F. Giannetti, B. Lasserre, M. Marchetti, G. Chirici // Sensors (Switzerland). - 2021. - Vol. 21, Issue 4. - 1182.
- Pereira, J.F.Q. Detection and identification of Cannabis sativa L. using near infrared hyperspectral imaging and machine learning methods / J.F.Q. Pereira, M.F. Pimentel, J.M. Amigo, R.S. Honorato // Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy. - 2020. -Vol. 237. - 118385.
- Ferreira, A. Eyes in the skies: A data-driven fusion approach to identifying drug crops from remote sensing images / A. Ferreira, S.C. Felipussi, R. Pires, S. Avila, G. Santos, J. Lambert, J. Huang, A. Rocha // IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. - 2019. - Vol. 12, Issue 12. - P. 4773-4786.
- Barton, I.F. Extending geometallurgy to the mine scale with hyperspectral imaging: a pilot study using drone- and ground-based scanning / I.F. Barton, M.J. Gabriel, J. Lyons-Baral, M.D. Barton, L. Duplessis, C. Roberts // Mining, Metallurgy and Exploration. - 2021. - Vol. 38, Issue 2. -P. 799-818.
- Degerick, J. Mapping functional urban green types using high resolution remote sensing data / J. Degerickx, M.Hermy, B. Somers // Sustainability. - 2020. - Vol. 12, Issue 5. - 2144.
- Huang, H. Underwater hyperspectral imaging for in situ underwater microplastic detection / H. Huang, Z. Sun, S. Liu, Y. Di, J. Xu, C. Liu, R. Xu, H. Song, S. Zhan, J. Wu // Science of the Total Environment. - 2021. - Vol. 776. -145960.
- Claudio, H.C. Monitoring drought effects on vegetation water content and fluxes in chaparral with the 970 nm water band index / H.C. Claudio, Y. Cheng, D.A. Fuentes, J.A. Gamon, H. Luo, W. Oechel, D.A. Sims // Remote Sensing of Environment. - 2006. - Vol. 103, Issue 3. - P. 304311.
- Mahajan, G.R. Using hyperspectral remote sensing techniques to monitor nitrogen, phosphorus, sulphur and potassium in wheat (Triticum aestivum L.) / G.R. Mahajan, R.N. Sahoo, R.N. Pandey, V.K. Gupta, D. Kumar // Precision agriculture. - 2014. - Vol. 15, Issue 5. - P. 499-522.
- Liu, B. A semi-supervised convolutional neural network for hyperspectral image classification / B. Liu, X. Yu, P. Zhang, X. Tan, A. Yu, Z. Xue // Remote Sensing Letters. - 2017. -Vol. 8. - P. 839-848.
- Bioucas-Dias, J.M. Hyperspectral remote sensing data analysis and future challenges / J.M. Bioucas-Dias, A. Plaza, G. Camps-Valls, P. Scheunders, N. Nasrabadi, J. Chanussot // IEEE Geoscience and Remote Sensing Magazine. - 2013. - Vol. 1. - P. 6-36.
- He, M. Multi-scale 3D deep convolutional neural network for hyperspectral image classification / M. He, B. Li, H. Chen // IEEE International Conference on Image Processing (ICIP). - 2017. - P. 3904-3908.
- Jung, A. Hyperspectral technology in vegetation analysis / A. Jung, P. Kardevan, L. Tokei // Progress in Agricultural Engineering Sciences. - 2006. - Vol. 2, Issue 1. - P. 95117.
- Kwan, C. An accurate vegetation and non-vegetation differentiation approach based on land cover classification / C. Kwan, D. Gribben, B. Ayhan, J. Li, S. Bernabe, A. Plaza // Remote Sensors. - 2020. - Vol. 12, Issue 23. - P. 3880-
- Hu, W. Deep convolutional neural networks for hyperspec-tral image classification / W. Hu, Y. Huang, L. Wei, F. Zhang, H. Li // Journal of Sensors. - 2015. - Vol. 2015. -P. 30-42.
- Nikonorov, A. Spectrum shape elements model to correct color and hyperspectral images / A. Nikonorov, S. Bibikov, P. Yakimov, V. Fursov // 2014 8th IAPR Workshop on Pattern Recognition in Remote Sensing. - 2014. - P. 1-4. -DOI: 10.1109/PRRS.2014.6914282.
- Nikonorov, A. Deep learning-based enhancement of hyper-spectral images using simulated ground truth / A. Nikonorov, M. Petrov, S. Bibikov, V. Kutikova, P. Yakimov, A. Morozov // 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS). - 2018. - P. 1-9. -DOI: 10.1109/PRRS.2018.8486408.
- Nikonorov, A. Correcting color and hyperspectral images with identification of distortion model / A. Nikonorov, S. Bibikov, V. Myasnikov, Y. Yuzifovich, V. Fursov // Pattern Recognition Letters. - 2016. - Vol. 83, Issue P2. -P. 178-187. - DOI: 10.1016/j.patrec.2016.06.027.
- Adao, T. Hyperspectral imaging: A review on UAV-based sensors, data processing and applications for agriculture and forestry / T. Adao, J. Hruska, L. Padua, J. Bessa, E. Peres, R. Morais, J.J. Sousa // Remote Sensing. - 2017. - Vol. 9, Issue 11. - 1110.
- Li, Y. Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network / Y. Li, H. Zhang, Q. Shen // Remote Sensors. - 2017. - Vol. 9(1). -P. 67-72.
- Chen, Y. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks / Y. Chen, H. Jiang, C. Li, X. Jia, P. Ghamisi // IEEE Transactions on Geoscience and Remote Sensing. - 2016. -Vol. 54, Issue 10. - P. 6232-6251.
- Xiu, Q. Attention-based pyramid network for segmentation and classification of high-resolution and hyperspectral remote sensing images / Q. Xu, X. Yuan, C. Ouyang, Y. Zeng // Remote Sensors. - 2020. - Vol. 12, Issue 21. - P. 35013507.
- Dobigen, N. Linear and nonlinear unmixing in hyperspectral imaging / N. Dobigeon, Y. Altmann, N. Brun, S. Moussaoui // Data Handling in Science and Technology. - 2016. - Vol. 30. - P. 185-224.
- Kale, K.V. Hyperspectral endmember extraction techniques / K.V. Kale, M.M. Solankar, D.B. Nalawade. - In: Processing and analysis of hyperspectral data / ed. by J. Chen, Y. Song, H. Li. - IntechOpen, 2019.
- Berk, A. MODTRAN6: a major upgrade of the MODTRAN radiative transfer code / A. Berk, P. Conforti, R. Kennett, T. Perkins, F. Hawes, J. van den Bosch // 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. - 2014. - P. 1-4.
- Подлипнов, В.В. Экспериментальное определение влажности почвы по гиперспектральным изображениям / В.В. Подлипнов, В.Н. Щедрин, А.Н. Бабичев, С.М. Васильев, В.А. Бланк // Компьютерная оптика. -2018. - Т. 42, № 5. - С. 877-884. - DOI: 10.18287/24126179-2017-42-5-877-884.
- Карпеев, С.В. Юстировка и исследование макетного образца гиперспектрометра по схеме Оффнера / C.B. Карпеев, С.Н. Хонина, А.Р. Мурдагулов, М.В. Петров // Вестник Самарского университета. Аэрокосмическая техника, технологии и машиностроение. - 2016. - Т. 15, № 1. - С. 197-206. - DOI: 10.18287/2412-7329-2016-15-1-197-206.
- Manea, D. Hyperspectral imaging in different light conditions / D. Manea, M.A. Calin // The Imaging Science Journal. - 2015. - Vol. 63. - P. 214-219.
- van de Weijer, J. Color constancy based on the Grey-edge hypothesis / J. van de Weijer, T. Gevers // IEEE International Conference on Image Processing. - 2005 - Vol. II. -P. 722-725.
- Cai, J. Facial expression recognition method based on sparse batch normalization CNN / J. Cai, Q. Chang, X.-L. Tang, C. Xue, C. Wei // 37th Chinese Control Conference (CCC). - 2018. - P. 9608-9613.
- Ioffe, S. Batch normalization: Accelerating deep network training by reducing internal covariate shift [Electronical Resource] / S. Ioffe, C. Szegedy // arXiv Preview. - 2015. -URL: https://arxiv.org/abs/1502.03167 (request date 31.08.2021).
- Luo, Y. HSI-CNN: A novel convolution neural network for hyperspectral image / Y. Luo, J. Zou, C. Yao, T. Li, G. Bai // International Conference on Audio, Language and Image Processing (ICALIP). - 2019. - P. 464-469.
- Ben Hamida, A. 3-D deep learning approach for remote sensing image classification / A. Ben Hamida, A. Benoit, P. Lambert, C. Ben Amar // IEEE Transactions on Geoscience and Remote Sensing. - 2018. - Vol. 56, Issue 8. -P. 4420-4434.
