The newest approach to the use of Normalized Difference Vegetation Index for the aerospace images classification with incomplete and inaccurate data.
DOI:
https://doi.org/10.34121/1028-9763-2022-2-19-28Keywords:
image classification, Normalized Difference Vegetation Index, parallelepiped method, Dempster’s rule, Inagaki’s combination rule, ecological monitoring, класифікування зображень, нормалізований диференційний вегетаційний індекс, метод паралелепіпедів, правило Демпстера, правило комбінування Інагакі, екологічний моніторингAbstract
Solution of different scientific, ecological and agricultural tasks with the use of aerospace images comprises a procedure of image classification. Classification is one of the most important procedures. Nowadays many supervised and unsupervised classification methods are applied in remote sensing. The most accurate results are obtained through the use of supervised classification methods. In this paper, there are proposed some new approaches to image classification which are based on supervised classification methods and Normalized Difference Vegetation Index (NDVI). Different values of NDVI are noted to correspond to different classes of objects, such as soil, water, roads, sand, green vegetation, oil spills. Application of Vegetation Index is the first step of classification. Using NDVI, it is possible to select special necessary classes. After the application of NDVI, such classification methods as the parallelepiped method, Dempster’s rule, and Inagaki’s combination rule can be used. The current work describes the main advantages of these classification methods. It has been noted that the use of the parallelepiped method allows easy and quick processing of data. The paper also shows that Dempster’s combination rule and Inagaki’s combination rule can deal with inaccurate and incomplete data from different spectral bands. Moreover, these methods can process conflicting information. Dempster-Shafer theory has the advantage of high accuracy and simple calculations. In the paper, there is also considered a numerical example where NDVI and Inagaki’s combination rule has been used for detection and mapping of oil spills. Application of Vegetation Index and such supervised classification rules as the parallelepiped method, Dempster’s rule, Inagaki’s combination rule can be applied in ecological monitoring, mapping of petroleum spills, and solving agricultural tasks.References
Chang C.I. Hyperspectral Data Processing: Algorithm Design and Analysis. Hoboken, NJ: John Willey & Sons, 2013. 1164 p.
Crippen R.E. Calculating the Vegetation Index Faster. Remote Sensing of Environment. 1990. Vol. 34. P. 71–73.
Huete A.R., Chen J., Jiang Z., Li J., Yan G., Zhang X., Chen Yu. Localización Analysis of NDVI and scaled difference vegetation index retrievals of vegetation fraction. Remote sensing of environment. 2016. Vol. 101, N 3. P. 366–378.
Хамедов В.А., Копылов В.Н., Полищук Ю.М., Шимов С.В. Использование данных дистанционного зондирования в задачах лесной отрасли. Современные проблемы дистанционного зондирования Земли из космоса: Физические основы, методы и технологии мониторинга окружающей среды, потенциально опасных объектов и явлений: сб. научн. ст. М.: ООО «Азбука-2000», 2006. С. 380–387.
Brownlee K.A. Statistical theory and methodology in science and engineering. New York: John Wiley and Sons, 1965. P. 580–590.
Renyi A. Probability theory. Amsterdam: North-Holland Pub. Co, 1970. 670 p.
Альперт С.І. Удосконалений метод комбінування даних на основі теорії Демпстера-Шейфера за наявності суперечливих даних. Математичні машини і системи. 2018. № 2. С. 33–39.
Abidi M.A., Gonzalez R.C. Data Fusion in Robotics and Machine Intelligence. New York: Academic, 1992. P. 562–569.
Congalton R.A. A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment. 1991. N 37. P. 35–46.
Гарбук С., Гершензон В. Космические системы дистанционного зондирования Земли. М.: Издво А и Б, 1997. 296 с.
Gong P. Integrated Analysis of Spatial Data from Multiple Sources: Using Evidential Reasoning and Artificial Neural Network Techniques for Geological Mapping. Photogrammetric Engineering and Remote Sensing. 1996. Vol. 62, N 5. P. 513–523.
Альперт С.І. Аналіз методів відбору найбільш інформативних спектральних каналів для вивчення об’єктів дистанційного зондування. Математичні машини і системи. 2014. № 2. С. 71–77.
Shafer G. A Mathematical Theory of Evidence. Princeton, NJ: Princeton University Press, 1976. P. 875–883.
Кузнецов А.В., Мясников В.В. Сравнение алгоритмов управляемой поэлементной классификации гиперспектральных изображений. Компьютерная оптика. 2014. Т. 38, № 3. С. 494–502.
Inagaki T. Interdependence between Safety-Control Policy and Multiple-Sensor Schemes Via Dempster-Shafer Theory. IEEE Transactions on Reliability. 1991. Vol. 40, N 2. P. 182–188.
Popov M., Alpert S., Podorvan V., Topolnytskyi M., Mieshkov S. Method of Hyperspectral Satellite Image Classification under Contaminated Training Samples Based on Dempster-Shafer’s Paradigm. Central European Researchers Journal. 2015. Vol. 1, N 1. P. 86–97.
Альперт С.І. Порівняння нового удосконаленого підходу комбінування суперечливих даних із правилом Ягера. Український журнал дистанційного зондування Землі. 2018. № 17. С. 14–17. URL: http://www. http://ujrs.org.ua/ujrs.
Лурье И.К., Косиков А.Г. Теория и практика цифровой обработки изображений. М.: Научный мир, 2003. 356 с.
60
15Published
Issue
Section
License
Copyright (c) 2022 Mathematical Machines and Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
