Increasing the Informativity of Multispectral Satellite Images Using Texture Analysis Data

Complete text of the article:

Download article (pdf, 3.2MB )

UDС

528.854(630*2)

DOI:

10.37482/0536-1036-2022-2-84-104

Abstract

The article considers the problem of incresing the informativity of multispectral images of medium (10–30 m) and high (1–4 m) spatial resolution obtained from foreign and national satellite remote sensing systems by involving additional textural information from panchromatic satellite images of very high spatial resolution (≲(1–0.4) m). The images of test sites on the territory of Savvat’yevo forestry (Tver region) from Landsat 8, Sentinel 2 and WorldView 2 satellites equipped with multispectral instruments were an object of this research. Geo-referenced ground survey data were used to validate the calculation results. We used the values of the spectral reflectance in the visible and near-infrared channels normalized to the appropriate integral characteristic as spectral features. Statistical characteristics were calculated in order to extract texture features based on the distribution of the co-occurrence of gray levels (Haralick texture features) within a moving window running the image with a given spatial step. A correlation analysis of textural features was carried out considering changes in distance and angle of adjacency. It was shown that for the selected leading features (autocorrelation, asymmetry, contrast and correlation) the first three can be used with an arbitrary direction of adjacency, while the latter needs to be considered in two different directions. Also we have found that all the considered classification algorithms provide a significant increase of accuracy when both spectral and textural features are used, in comparison with the traditional spectral classification. This result was shown for all images of test sites obtained by different satellites. It is possible to make a preliminary conclusion that the proposed integrated approach of thematic processing can improve the quality of object recognition in the case of using images of both medium and high spatial resolution. Estimates obtained during the thematic mapping of dominant and subdominant forest species showed close classification accuracies for different initial multispectral images (with a scatter of no more than 5 % around the average value of 85 %). Mostly this is due to the presence of specific errors in the ground-based forest inventory data and indicates the necessity of their updating with the use of satellite remote sensing images.

---

This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) license • The authors declare that there is no conflict of interest

Authors

Sergey A. Zotov¹, Postgraduate Student; ResearcherID: AAN-7199-2020, ORCID: https://orcid.org/0000-0002-3483-1449
Egor V. Dmitriev^{1, 2}, Candidate of Physics and Mathematics, Senior Research Scientist; ResearcherID: E-4794-2014, ORCID: https://orcid.org/0000-0001-5363-3934
Petr G. Melnik^3,4, Candidate of Agriculture, Assoc. Prof.; ResearcherID: E-7644-2014, ORCID: https://orcid.org/0000-0002-2802-7614
Timofey V. Kondranin¹, Doctor of Physics and Mathematics; ResearcherID: K-9407-2013, ORCID: https://orcid.org/0000-0003-3565-3194

Affiliation

¹Moscow Institute of Physics and Technology, Institutskiy per., 9, Dolgoprudny, Moscow Region, 141701, Russian Federation; e-mail: zotov.sa@mipt.ru, kondr@kondr.rector.mipt.ru
²Marchuk Institute of Numerical Mathematics RAS, ul. Gubkina, 8, Moscow, 119333, Russian Federation; e-mail: yegor@mail.ru
³Mytischi Branch of Bauman Moscow State Technical University, ul. 1-ya Institutskaya, 1, Mytischi, Moscow Region, 141005, Russian Federation; e-mail: melnik_petr@bk.ru
⁴Institute of Fоrеst Science, Russian Academy of Sciences, ul. Sovetskaya, 21, s. Uspenskoe, Moscow Region, 143030, Russian Federation; e-mail: melnik_petr@bk.ru

Funding

The work was carried out with the financial support of the Russian Foundation for Basic Research; project No. 20-07-00370 “Fundamental Problems of Improving the Informativity of Data Processing of Optoelectronic Aerospace Devices with High Spatial and Spectral Resolution”.

For citation

Zotov S.A., Dmitriev E.V., Melnik P.G., Kondranin T.V. Increasing the Informativity of Multispectral Satellite Images Using Texture Analysis Data. Lesnoy Zhurnal [Russian Forestry Journal], 2022, no. 2, pp. 84–104. DOI: 10.17238/issn0536-1036-2022-2-84-104

References

1. Воронина П.В., Мамаш Е.А. Классификация тематических задач мониторинга сельского хозяйства с использованием данных дистанционного зондирования MODIS // Вычислительные технологии. 2014. Т. 19, № 3. C. 76–102. Voronina P.V., Mamash E.A. Classification of Thematic Monitoring for Agriculture Problems Using Remote Sensing MODIS Data. Vychislitelnye tekhnologii [Computational Technologies], 2014, vol. 19, no. 3, pp. 76–102.

2. Колодникова Н.В. Обзор текстурных признаков для задач распознавания образов // Докл. ТУСУР. 2004. № 1(9). С. 113–124. Kolodnikova N.V. Overview of Textural Features for Pattern Recognition Problems. Doklady TUSUR [Proceedings of TUSUR University], 2004, no. 1(9), pp. 113–124.

3. Потапов A.А. Новые информационные технологии на основе вероятностных текстурных и фрактальных признаков в радиолокационном обнаружении малоконтрастных целей // Радиотехника и электроника. 2003. Т. 48, № 9. С. 1101–1119. Potapov A.A. New Information Technology in Radar Detection of Low-Contrast Targets Based on Probabilistic Texture and Fractal Features. Radiotehnika i elektronika [Journal of Communications Technology and Electronics], 2003, vol. 48, no. 9, pp. 1101–1119.

4. Фраленко В.П. Методы текстурного анализа изображений, обработка данных дистанционного зондирования Земли // Программные системы: теория и приложения. 2014. Т. 5, № 4(22). С. 19–39. Fralenko V.P. Methods of Image Texture Analysis, Earth Remote Sensing Data Processing. Programmnyye sistemy: teoriya i prilozheniya [Program Systems: Theory and Applications], 2014, no. 4(22), pp. 19–39.

5. Шабанов Н.В., Барталев С.А., Ерошенко Д.А., Плотников Ф.В. Развитие возможностей дистанционной оценки индекса листовой поверхности по данным MODIS // Современные проблемы дистанционного зондирования Земли из космоса. 2018. Т. 15, № 4. С. 166–178. Shabanov N.V., Bartalev S.A., Eroshenko F.V., Plotnikov D.E. Development of Capabilities for Remote Sensing Estimate of Leaf Area Index from MODIS Data. Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa [Current problems in remote sensing of the Earth from space], 2018, vol. 15, no. 4, pp. 166–178. DOI: https://doi.org/10.21046/2070-7401-2018-15-4-166-178

6. Beguet B., Guyon D., Boukir S., Chehata N. Automated Retrieval of Forest Structure Variables Based on Multi-Scale Texture Analysis of VHR Satellite Imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, vol. 96, pp. 164–178. DOI: https://doi.org/10.1016/j.isprsjprs.2014.07.008

7. Breiman L. Random Forests. Machine Learning, 2001, vol. 45, iss. 1, pp. 5–32. DOI: https://doi.org/10.1023/A:1010933404324

8. Brynolfsson P., Nilsson D., Torheim T., Asklund T., Thellenberg Karlsson C., Trygg J., Nyholm T., Garpebring A. Haralick Texture Features from Apparent Diffusion Coefficient (ADC) MRI Images Depend on Imaging and Pre-Processing Parameters. Scientific Reports, 2017, vol. 7, art. 4041. DOI: https://doi.org/10.1038/s41598-017-04151-4

9. Chen J.M., Cihlar J. Retrieving Leaf Area Index of Boreal Conifer Forests Using Landsat TM images. Remote Sensing of Environment, 1996, vol. 55, iss. 2, pp. 153–162. DOI: https://doi.org/10.1016/0034-4257(95)00195-6

10. Cover T.M., Hart P.E. Nearest Neighbor Pattern Classification. IEEE Transactions on Information Theory, 1967, vol. 13, no. 1, pp. 21–27. DOI: https://doi.org/10.1109/TIT.1967.1053964

11. Dmitriev E.V., Sokolov A.A., Kozoderov V.V., Delbarre H., Melnik P.G., Donskoi S.A. Spectral Texture Classification of High-Resolution Satellite Images for the State Forest Inventory in Russia. Remote Sensing for Agriculture, Ecosystems, and Hydrology XXI, 2019, vol. 11149, art. 111491J. DOI: https://doi.org/10.1117/12.2532965

12. Eklundh L., Harrie L., Kuusk A. Investigating Relationships between Landsat ETM+ Sensor Data and Leaf Area Index in a Boreal Conifer Forest. Remote Sensing of Environment, 2001, vol. 78, iss. 3, pp. 239–251. DOI: https://doi.org/10.1016/S0034-4257(01)00222-X

13. Ferreira M.P., Wagner F.H., Aragão L.E.O.C., Shimabukuro Y.E., de Souza Filho C.R. Tree Species Classification in Tropical Forests Using Visible to Shortwave Infrared WorldView-3 Images and Texture Analysis. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, vol. 149, pp. 119–131. DOI: https://doi.org/10.1016/j.isprsjprs.2019.01.019

14. Franklin S.E. Remote Sensing for Sustainable Forest Management. Boca Raton, FL, CRC press, 2001, p. 424. DOI: https://doi.org/10.1201/9781420032857

15. Goldberger J., Hinton G.E., Roweis S., Salakhutdinov R.R. Neighbourhood Components Analysis. Advances in Neural Information Processing Systems 17: Proceedings of the 2004 Conference. Ed. by L. Saul, Y. Weiss, L. Bottou. Cambridge, MA, MIT Press, 2004, pp. 513–520.

16. Hadi H., Korhonen L., Hovi A., Rönnholm P., Rautiainen M. The Accuracy of Large-Area Forest Canopy Cover Estimation Using Landsat in Boreal Region. International Journal of Applied Earth Observation and Geoinformation, 2016, vol. 53, pp. 118–127. DOI: https://doi.org/10.1016/j.jag.2016.08.009

17. Haralick R.M. Statistical and Structural Approaches to Texture. Proceedings of the IEEE, 1979, vol. 67, no. 5, pp. 786–804. DOI: https://doi.org/10.1109/PROC.1979.11328

18. Haralick R.M., Shanmugam K., Dinstein I. Textural Features for Image Classification. IEEE Transactions on Systems, Man, and Cybernetics, 1973, vol. SMC-3, no. 6, pp. 610–621. DOI: https://doi.org/10.1109/TSMC.1973.4309314

19. Lechner A.M., Foody G.M., Boyd D.S. Applications in Remote Sensing to Forest Ecology and Management. One Earth, 2020, vol. 2, iss. 5, pp. 405–412. DOI: https://doi.org/10.1016/j.oneear.2020.05.001

20. Paletto A., Tosi V. Forest Canopy Cover and Canopy Closure: Comparison of Assessment Techniques. European Journal of Forest Research, 2009, vol. 128, iss. 3, pp. 265–272. DOI: https://doi.org/10.1007/s10342-009-0262-x

21. Sexton J.O., Song X.-P., Feng M., Noojipady P., Anand A., Huang C., Kim D.-H., Collins K.M., Channan S., DiMiceli C., Townshend J.R. Global, 30-m Resolution Continuous Fields of Tree Cover: Landsat-Based Rescaling of MODIS Vegetation Continuous Fields with Lidar-Based Estimates of Error. International Journal of Digital Earth, 2013, vol. 6, iss. 5, pp. 427–448. DOI: https://doi.org/10.1080/17538947.2013.786146

22. Srivastava S., Gupta M.R., Frigyik B.A. Bayesian Quadratic Discriminant Analysis. Journal of Machine Learning Research, 2007, vol. 8, pp. 1277–1305.

23. Tharwat A. Linear vs. Quadratic Discriminant Analysis Classifier: A Tutorial. International Journal of Applied Pattern Recognition, 2016, vol. 3, no. 2, pp. 145–180. DOI: https://doi.org/10.1504/IJAPR.2016.079050