Object-Oriented Classification of Substrate Surface Objects in Arctic Impact Regions Aerospace Monitoring

The paper proposes a method for recognition of earth surface types according to space images using object-oriented classification. The classification is conducted in two stages: Markov stochastic segmentation for object extraction and supervised classification of the objects. The method is tested on space imagery of the Russian Arctic in comparison with point-oriented classification.

References

[1] Bondur V.G., Vorob’yev V.E. Space monitoring of Arctic impact regions. Issledovanie Zemli iz kosmosa, 2015, no. 4, pp. 3-24 (in Russ.). DOI: 10.7868/S0205961415040028

[2] Bondur V.G. Modern approaches to the processing of huge hyperspectral and multispectral airspace data flow. Issledovanie Zemli iz kosmosa, 2014, no. 1, pp. 4-16 (in Russ.). DOI: 10.7868/S0205961414010035

[3] Bondur V.G. Space monitoring of naturally-occurring fires in Russia in anomalous heat conditions of 2010. Issledovanie Zemli iz kosmosa, 2011, no. 3, pp. 3-13 (in Russ.).

[4] Bondur V.G. Airspace monitoring methods and technologies of oil-and-gas territories and objects. Issledovanie Zemli iz kosmosa, 2010, no. 6, pp. 3-17 (in Russ.).

[5] Bondur V.G., Gaponova M.V., Murynin A.B., Trekin A.N. Modul’ O obucheniya klassifikatorov dlya kosmicheskikh snimkov nizkogo i vysokogo razresheniya [Learning package O for high and low resolution space images classifier]. Svidel’stvo o gosudarstvennoy registratsii programmy dlya EVM № 2013614299. Data gosudarstvennoy registratsii v Reestre programm dlya EVM 29 aprelya 2013 g [Software certificate of registration № 2013614299. Reg. date: 25.04.2013] (in Russ.).

[6] Ignatiev V.Yu., Murynin A.B., Trekin A.N. Object oriented space images classification method for impact regions monitoring. Otkrytiya i dostizheniya nauki: Sbornik materialov mezhdunarodnoy nauchnoy konferentsii [Scientific discoveries and achievements. Proc. int. sci. conf.]. 2015, pp. 176-186 (in Russ.).

[7] Blaschke T., Johansen K., Tiede D., Weng Q., ed. Object-based image analysis for vegetation mapping and monitoring. In: Advances in environmental remote Sensing: sensors, algorithms, and applications. CRC Press, 2011. P. 241-272. DOI: 10.1201/b10599-13 Available at: http://www.crcnetbase.com/doi/abs/10.1201/b10599-13

[8] Rougier S., Puissant A., Stumpf A., Lachiche N. Comparison of sampling strategies for object-based classification of urban vegetation from very high resolution satellite images. International Journal of Applied Earth Observation and Geoinformation, 2016, vol. 51, pp. 60-73.

[9] Vahidi H., Monabbati E. Contextual image classification approach for monitoring of agricultural land cover by support vector machines and Markov random fields. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2013, vol. XL-1/W3 / SMPR 2013, 5-8 October 2013, Tehran, Iran.

[10] Burnett C., Dlaschke T. A multi-scale segmentation/object relationship modelling methodology for landscape analysis. Ecological Modelling, 2003, vol. 168, no. 3, pp. 233-249.

[11] Stankova H. Object-oriented classification of Landsat imagery and aerial photographs for land cover mapping. Proceedings - Symposium GIS Ostrava, 2010, 24-27 January 2010.

[12] Marangoz A.M., Oruc M., Karakis S., Sahin H. Comparison of pixel-based and object-oriented classification using Ikonos imagery for automatic building extraction - Safranbolu testfield. 5th Int. Symp. "Turkish-German Joint Geodetic Days", Berlin Technical University, 28-31 March 2006.

[13] Flanders D., Hall-Beyer M., Pereverzoff J. Preliminary evaluation of eCognition object-based software for cut block delineation and feature extraction. Canadian Journal of Remote Sensing, 2003, vol. 29, no. 4, pp. 441-452.

[14] Verbeeck K., Van Orshoven J. External geoinformation in the segmentation of VHR imagery improves the detection of imperviousness in urban neighborhoods. International Journal of Applied Earth Observation and Geoinformation, 2012, vol. 18, no. 1, pp. 428-435.

[15] Chen G., Hay G.J., Carvalho L.M.T., Wulder M.A. Object-based change detection. International Journal of Remote Sensing, 2012, vol. 33, no. 14, pp. 4434-4457. DOI: 10.1080/01431161.2011.648285 Available at: http://www.tandfonline.com/doi/abs/10.1080/01431161.2011.648285

[16] Benz U.C., Hofmann P., Willhauck G., Lingenfelder I., Heynen M. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS Journal of Photogrammetry and Remote Sensing, 2003, vol. 58, no. 3-4, pp. 239-258.

[17] Bondur V.G. Osnovy aerokosmicheskogo monitoringa okruzhayushchey sredy. Kurs lektsiy [Fundamentals of airspace environment monitoring. Lecture course]. Moscow, MIIGAiK Publ., 2008. 546 p.

[18] Takahashi K., Kamagata N., Hara K. Object-oriented image analysis to extract landscape elements in urban fringes, Central Japan. Landscape and Ecological Engineering, 2013, vol. 9, no. 2, pp. 239-247. DOI: 10.1007/s11355-012-0202-7 Available at: https://link.springer.com/article/10.1007/s11355-012-0202-7

[19] Besag J. On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society. Series B, 1986, vol. 48, no. 3, pp. 259-302. Available at: http://www.jstor.org/stable/2345426?seq=1#page_scan_tab_contents

[20] Srivastava S., Gupta M.R., Frigyik B.A. Bayesian quadratic discriminant analysis. Journal of Machine Learning Research, 2007, no. 8, pp. 1277-1305. Available at: http://jmlr.csail.mit.edu/papers/v8/srivastava07a.html

[21] Wu W., et al. Comparison of regularized discriminant analysis linear discriminant analysis and quadratic discriminant analysis applied to NIR data. Analytica Chimica Acta, 1996, vol. 329, no. 3, pp. 257-265. DOI: 10.1016/0003-2670(96)00142-0 Available at: http://www.sciencedirect.com/science/article/pii/0003267096001420

[22] Haralick R.M., Shanmugam K., Dinstein I. Textural features for image classification. IEEE Trans. Syst. Man and Cybernetics, 1973, vol. 3, no. 6, pp. 610-621.