528.7

В статье исследуется временная изменчивость площадей лесных массивов провинции Эпена (Республика Конго) по материалам космических съемок. В этом исследовании сравнивались пиксельные и объектно-ориентированные классификации с использованием спутникового изображения LANDSAT-8, было проведено первое исследование для поиска подходящего метода классификации. Выполненное исследование показывает, что объектно-ориентированная классификация даёт более точные и удовлетворительные результаты. Общая точность объектно-ориентированной классификации составила 89.05%, в то время как такая классификация на основе пикселей дала 70.16%, от 0.60 до 0.82 для индекса Каппа. Далее было проведено второе исследование по объектно-ориентированной классификации за период с 2016 по 2018 гг. Общая точность объектно-ориентированной классификации в 2016 составила 87.25% и индекс Каппа 0.80; а в 2018 она составила 90.85% и индекс Каппа 0.83.

The paper examines the temporal variability of forest areas in the province of Epena (Republic of the Congo) based on space survey materials. This study compared pixel and object-oriented classifications using the LANDSAT-8 satellite images. The first conducted study to find a suitable classification method showed that object-oriented classification gives more accurate and satisfactory results. The overall accuracy of the object-oriented classification was 89.05%, while the pixel-based classification yielded 70.16%, ranging from 0.60 to 0.82 for the Kappa index. Next, a second study was conducted on object-oriented classification for the period from 2016 to 2018. The overall accuracy of the object-oriented classification in 2016 was 87.25% and the Kappa index was 0.80; and in 2018 it was 90,85% and the Kappa index was 0.83.

аспирант, кафедра космического мониторинга и экологии Московского государственного университета геодезии и картографии

Rozenstein O., & Karnieli A. (2011). Comparison of methods for land-use classification incorporating remote sensing and GIS inputs. Applied Geography. 31(2). 533-544.

Aguirre-Gutierrez J., Seijmonsbergen A.C., & Duivenvoorden J.F. (2012). Optimizing land cover classification accuracy for change detection, a combined pixel-based and object-based approach in a mountainous area in Mexico. Applied Geography. 34. 29-37.

Berberoglu S., & Curran P.J. (2004). Merging spectral and textural information for classifying remotely sensed images. In Remote sensing image analysis: including the spatial domain. Springer Netherlands. 113-136.

Ming D., Li J., Wang J., & Zhang M. (2015). Scale parameter selection by spatial statistics for GeOBIA: Using mean-shift based multi-scale segmentation as an example. ISPRS Journal of Photogrammetry and Remote Sensing. 106: 28-41.

Fu K.S., & Mui J.K. (1981). A survey on image segmentation. Pattern recognition. 13(1). 3-16.

Haralick R.M., & Shapiro L.G. (1985). Image segmentation techniques. Computer vision, graphics, and image processing. 29(1). 100-132.

Blaschke T. (2010). Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing 65 (2010): 2-16.

Myint S.W., Gober P., Brazel A., Grossman-Clarke S. & Weng Q. (2011). Per-pixel vs. objectbased classification of urban land cover extraction using high spatial resolution imagery. Remote sensing of environment. 115(5): 1145-1161.

Zhou W.Q., & Troy A. (2008). An object-oriented approach for analysing and characterizing urban landscape at the parcel level. International Journal of Remote Sensing. 29: 3119-3135.

Bock M., Xofis P., Mitchley J., Rossner G., & Wissen M. (2005). Object-oriented methods for habitat mapping at multiple scales-Case studies from Northern Germany and Wye Downs, UK. Journal for Nature Conservation. 13(2): 75-89.

Gurkan A. (2016). Biotope mapping in an urban environment for sustainable urban development ? a case study in southern part of turkey. Applied ecology and environmental research. 14(4): 493-504.

Willhauck G., Schneider T., De Kok R., & Ammer U. (2000). Comparison of object-oriented classification techniques and standard image analysis for the use of change detection between SPOT multispectral satellite images and aerial photos. In Proceedings of XIX ISPRS congress (Vol. 33. Pp. 35-42).

Adam H.E., Csaplovics E., & Elhaja M.E. (2016). A comparison of pixel-based and object-based approaches for land use land cover classification in semi-arid areas, Sudan. In IOP Conference Series: Earth and Environmental Science (Vol. 37. No. 1. Pp. 012061). IOP Publishing.

User Guide, eCognition Developer 8.7 - Trimble Documentation. Munchen. Germany. 2011.

Denfinies, eCognition User guide. 2007. Pp. 27.

ENVI User Guide - ENVI Version 4.1. 2004.

https://fr.wikipedia.org/wiki/Likouala_(d%C3%A9partement).

Anders N.S., Seijmonsbergen A.C., Bouten W. Segmentation optimization and stratified objectbased analysis for semi-automated geomorphological mapping. Remote Sens Environ. 2011; 115(12): 2976-2985. https://doi.org/10.1016/j.rse.2011.05.007.

Dragut L., Tiede D., Levick S.R. ESP: A tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data. Int J Geogr Inf Sci. 2010; 24(6): 859-871. https://doi.org/10.1080/13658810903174803.

Н.В. Малышева. Основы автоматизированного дешифрирование аэрокосмических снимков лесов с использованием ГИС // учебное пособие. 2020.

Object Based and Pixel Based Classification using Rapid eye Satellite Imagery of EtiOsa. Lagos. Nigeria.