Automatized recognition of urban vegetation and water bodies by Jilin-1А satellite images

Heading: 
Study of the Earth from Space
1Makarov, AL, 2Belousov, KG, 3Svinarenko, DN, 1Khoroshylov, VS, 3Mozgovoy, DK, 1Popel', VM
1Yangel Yuzhnoye State Design Office, Dnipro, Ukraine
2Yuzhnoye State Design Office, Dnipro, Ukraine
3Oles Honchar Dnipro National University, Dnipro, Ukraine
Space Sci. & Technol. 2021, 27 ;(4):42-53
https://doi.org/10.15407/knit2021.04.042
Publication Language: Ukrainian
Abstract: 
The results of testing the developed techniques for automatized recognition of vegetation and water bodies on the urban territory by multispectral images from the Jilin-1А satellite are given.The research included automatized recognition of vegetation and water bodies on the selected observation territory based on images with super high spatial resolution in the visual and infrared range and consequent comparison of the obtained results with the results of visual decoding.
      The obtained results of processing the images from the Jilin-1А satellite in accordance with the proposed techniques confirmed the sufficiently high accuracy of automatized edge enhancement of recognized objects as compared to the results of interactive visual recognition of these images. Different test areas provided a good separation of vegetation and water types with the same thresholding customization.
      The accuracy of automatized classification of vegetation and water bodies (without considering the standard errors) for different test areas was within 81...92%, and values of kappa-coefficient were within 0.68 to 0.85.
      Comparison of normalized index images received from Jilin-1А and Sentinel-2A satellites showed slight discordance in NDVI values and significant discordances for NDWI and MNDWI that are caused by the usage of different spectral channels (SWIR and NIR). These discordances can be sufficiently reduced when using correction coefficients.Analysis of the influence of output image resolution reduction (from 10 to 8 bit) and subsequent informational compressing (JPEG lossy and JPEG2000 lossless) on results of automatized recognition of vegetation and water bodies confirmed the validity and efficiency of these techniques. The volume of saved and transmitted files significantly decreased (in 80…100 times) with a slight reduction of classification accuracy (by 1...2 %).
       The proposed techniques make it possible to increase significantly the efficiency and probability of renewing maps of big cities and to reduce financial expenditures as compared to the traditional ground GPS-surveying and aerosurveying.
The high-level automatization of image processing and minimization of necessary calculations (as compared to techniques that use complex classifiers and neural networks) allow to implement the developed technique as a geographic information web service that satisfies the needs of a wide circle of government services and commercial structures and can be useful for megalopolis population and tourists.
Keywords: image processing, map renewal, multispectral images, satellite monitoring, spectral indices
Full text (PDF)
References: 
1. Bardysh B., Burshtynska H. (2014). The use of vegetation indices to identify objects on the Earth’s surface. Suchasni dosyagnennya geodezychnoyi nauky ta vyrobnyctva, 2, 82—88 [In Ukrainian].
2. Belenok V. Yu., Derkach D. I., Rul N. V. (2017). Vykorystannya aerokosmichnyh metodiv ta metodiv obrobky danykh dystancijnoho zonduvannya Zemli dlya ekologichnogo monitoryngu Kahovskogo vodoskhovyscha. Visnyk Astron. shkoly, 13, No 1, 54—63 [In Ukrainian].
3. Burshtynska Kh. V., Polishchuk B. V., Kovalchuk O. Yu. (2013). Research of methods for classification of forests using satellite images of high resolution. Geodeziya, kartografiya ta aerofotoznimannya, 78, 101—110.
4. Vyshnevskyi V. I., Shevchuk S. A. (2016). Evaluation of status of Kyiv water bodies using remote sensing data. Ukr. J. remote sensing, No 11, 9—14 [In Ukrainian].
5. Zatserkovnyi V. I., Oberemok N. V., Tishaev I. V., Kazanyuk T. A. (2017). Use of technologies of geoinformation systems and remote sensing of the Earth for monitoring of water objects. Science-Based Technologies, No 1 (33), 78—88 [In Ukrainian].
6. Kravchenko O. M., Lavrenyuk M. S., Kussul N. M. (2013). Sich-2 satellite image georeferencing algorithm. Works of DonNTU. Ser. Informatics, Cybernetics and Computer Science, No 2 (18), 71—79 [In Ukrainian].
7. Kussul N. M., Basarab R. M., Kravchenko O. M., Lavrenyuk M. S., Krygin V. M., Reva K. V. (2014). Software technical complex automatically geographical binding of satellite Sich 2 remote sensing data. Programming Problems, No 2-3, 303—311 [In Ukrainian].
8. Kussul N. M., Shelestov A. Yu., Yailymov B. Ya., Shumilo L. L., Yailymova H. O., Lavreniuk M. S., Kolos L. M., Pidgorodetska L. V. (2019). Urban Atlas for Ukrainian cities on the basis of high-resolution satellite data. Space Science and Technology, 25(6), 51—60 [In Ukrainian].
9. Mozgovoj D. K. (2018). Operational satellite monitoring vegetation and water objects in the territory of cities. Ukr. J. remote sensing, No 17, 18—25 [In Russian].
10. Mozgovoy D. K., Vasil’yev V. V. (2016). Monitoring of natural and anthropogenic processes using the Landsat Viewer web service. Bull. DNU. Rocket and space technology, 24 (4), 13, 95—101 [In Russian].
11. Pazinich N. V., Lischenko L. P., Mychak A. G., Filipovych V. Ye., Teremenko O. M. (2015). Decision of task of ecological geomorphologic in the Kyiv city with the use of remote sensing data (on the example of Lybid river valley). Ukr. J. remote sensing, 5, 33—36 [In Ukrainian].
12. Pestova I. O. (2015). Methods of estimating the state of vegetation of urban areas using multispectral space images: Dis. ... Cand. tech. Sci. Kyiv. [In Ukrainian].
13. Sokolovska A. V. (2013). Space monitoring of ecological condition of urban territories (the Kyiv city is used as an example). Kosm. nauka tehnol., 19(4), 44—49 [In Ukrainian].
14. Stankevich S. A., Pestova I. A. (2014). Vegetation cover changes mapping within Kiev metropolis agglomeration using long-term time series of Landsat multispectral satellite imagery. Modern problems of remote sensing of the Earth from space, 11,  No 2, 187—196 [In Russian].
15. Stankevich S. A., Pestova I. O. (2014). Geoinformation service of data processing for estimation of a condition of vegetation  of the urbanized territories. Bulletin of Geodesy and Cartography, No 3, 23—26 [In Ukrainian].
16. Tomchenko O. V., Khyzhnyak A. V. (2016). Vegetation indices as a tool for assessing and monitoring the state of land resources. Emerging technologies, 1(1), 13—15 [In Ukrainian].
17. Ulytsky О., Yermakov V., Lunova О., Buglak O. (2019). Technique for orthotransformed satellite imagery application in environmental assessment. Space Science and Technology, 25(4), 48—56 [In Ukrainian].
18. Fedorovskyi A. D., Khyzhniak A. V., Diachenko T. N., Yakimchuk V. G., Pidhorniak D. L., Sukhanov K. Yu., Tomchenko O. V. (2017). Space monitoring of water stream in estuarial areas (by the example of the Dnieper and the Danube). Space Science and Technology, 23(2), 11—16 [In Ukrainian].
19. Filipovych V. Ye. (2013). Features of space monitoring of urban landscapes. Phys. geogr. and geomorphol. 3, 143—150 [In Ukrainian].
20. Shapar A. H., Taranenko O. S. (2018). Determination of technogenic and natural changes in the mining landsby remote sensing data. Ecological safety, No 2 (26), 61—69 [In Ukrainian].
21. Shevchuk S. A., Shevchenko I. A. (2013). Determination of ecological condition of reservoirs by means of methods of remote monitoring. Land Reclamation and Water Management, 100(2), 42—53 [In Ukrainian].
22. Yailymov B. Ya., Lavreniuk M. S., Shelestov A. Yu., Kolotii A. V., Yailymova H. O., Fedorov O. P. (2018). Methods of essential variables determination for the Earth’s surface state assessing. Space Science and Technology, 24(4), 24—37 [In Ukrainian].
23. Mozgovoy D. K., Hnatushenko V. V., Vasyliev V. V. (2018). Automated recognition of vegetation and water bodies on the territory of megacities in satellite images of visible and IR bands. ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-3, 167—172.
24. Mozgovoy D., Hnatushenko V., Vasyliev V. (2018). Accuracy evaluation of automated object recognition using multispectral aerial images and neural network. Int. Conf. on Digital Image Processing. Shanghai, East China Normal University.
25. Satellite Missions Database. URL: https://directory.eoportal.org/web/eoportal/satellite-missions (Last accessed: 19.10.2020)