Comparison Analysis of Recognition Algorithms of Forest-Cover Objects on Hyperspectral Air-Borne and Space-Borne Images
The basic model for the recognition of natural and anthropogenic objects using their spectral and textural features is described in the problem of hyperspectral air-borne and space-borne imagery processing. The model is based on improvements of the Bayesian classifier that is a computational procedure of statistical decision making in machine-learning methods of pattern recognition. The principal component method is implemented to decompose the hyperspectral measurements on the basis of empirical orthogonal functions. Application examples are shown of various modifications of the Bayesian classifier and Support Vector Machine method. Examples are provided of comparing these classifiers and a metrical classifier that operates on finding the minimal Euclidean distance between different points and sets in the multidimensional feature space. A comparison is also carried out with the “K-weighted neighbors” method that is close to the nonparametric Bayesian classifier.
Keywordshyperspectral air-borne and space-borne imagery natural-and anthropogenic-object pattern recognition optimization of data processing
Unable to display preview. Download preview PDF.
- Cost, S. and Salzberg, S., A weighted nearest neighbor algorithm for learning with symbolic features, Mach. Learn., 1993, vol. 10, no. 1, pp. 57–78.Google Scholar
- Fukunaga, K., Introduction to Statistical Pattern Recognition, New York: Academic, 1990.Google Scholar
- Jolliffe, I.T., Principal Component Analysis, Springer, 2002.Google Scholar
- Kozoderov, V.V. and Dmitriev, E.V., Remote sensing of forest cover: An innovative approach, Vestn. Mosk. Gos. Univ. Lesa–Lesn. Vestn., 2012a, no. 1, pp. 19–33.Google Scholar
- Kozoderov, V.V., Kondranin, T.V., Dmitriev, E.V., Kazantsev, O.Yu., Persev, I.V., and Shcherbakov, M.V., Processing of hyperspectral aerospace sounding data, Issled. Zemli Kosmosa, 2012, no. 5, pp. 3–11.Google Scholar
- Kozoderov, V.V., Dmitriev, E.V., and Kamentsev, V.P., System for processing of airborne images of forest ecosystems using high spectral and spatial resolution data, Issled. Zemli Kosmosa, 2013a, no. 6, pp. 57–64.Google Scholar
- Kozoderov, V.V., Kondranin, T.V., and Dmitriev, E.V., Metody obrabotki mnogospektral’nykh i giperspektral’nykh aerokosmicheskikh izobrazhenii. Uchebnoe posobie (Methods of Processing of Multispectral and Hyperspectral Aerospace Images: A Textbook), Moscow: MFTI, 2013b.Google Scholar
- Kozoderov, V.V., Kondranin, T.V., Dmitriev, E.V., and Kamentsev, V.P., A system for processing hyperspectral imagery: Application to detecting forest species, Int. J. Remote Sens., 2014d, vol. 35, no. 15, pp. 5926–5945.Google Scholar
- Kozoderov, V.V., Dmitriev, E.V., and Sokolov, A.A., Cognitive technologies in optical remote sensing data processing, Clim. Nature, 2015c, no. 1, pp. 5–45.Google Scholar
- Kozoderov, V.V., Kondranin, T.V., Dmitriev, E.V., and Kamentsev, V.P., Validation of information products of processing of aircraft hyperspectral images, Issled. Zemli Kosmosa, 2015d, no. 1, pp. 32–43.Google Scholar
- Shovengerdt, R.A., Distantsionnoe zondirovanie. Modeli i metody obrabotki izobrazhenii (Remote Sensing. Models and Methods of Image Processing), Moscow: Tekhnosfera, 2010.Google Scholar
- Tou, J. and Gonzales R., Pattern Recognition Principles, Reading, MA: Addison-Wesley, 1974; Moscow: Mir, 1978.Google Scholar