519.2 Application of a finite mixture model in radar image processing
Dostavalova A. M. (Bauman Moscow State Technical University)
MIXTURE OF DISTRIBUTIONS, TARGET DETECTION ON RADAR IMAGES, IDENTIFIABILITY, ЕМ-ALGORITHM, NORMAL DISTRIBUTION MODEL, LOCAL ESTIMATION OF MIXTURE PARAMETER, BAYESIAN INFORMATION CRITERION, FINITE MIXTURE.
doi: 10.18698/2309-3684-2020-3-117130
The problem of target detection on a radar image (RI) is considered. When solving it, it is proposed to use a finite mixture as a model describing the structure of the processed image. It is assumed that each of its components corresponds to one of the classes of objects present on the radar image, which are similar in their reflective properties. This hypothesis allows one to detect targets by solving the problem of finite mixture separating. It is possible to use for this existing methods of mixture decomposition — the EM-algorithm. However, the structure of the image, in which target classes are local inhomogeneities, consisting of a small number of samples, imposes restrictions on the possibility of using these algorithms in their pure form and leads to the need to create their adaptations that take into account this feature of the input data. The article presents the results of applying the adapted EM-algorithm using the generated radar image with pixels obeying the normal law as an input data. The efficiency of the created algorithm is assessed in comparison with the results of applying the classical version of the EM-algorithm for this model. The data obtained made it possible to reveal the peculiarities of the method due to both the created mechanics of image processing and the properties of the procedure for separating mixtures — the EM-algorithm, which must be taken into account in the further use of this method of image processing.
[1] Kayabol K., Krylov V.A., Zerubia, J. Unsupervised classification of SAR images using hierarchical agglomeration and EM. Lecture Notes in Computer Science, 2012, vol. 7252, pp. 54–65.
[2] Колфилд Г. Оптическая голография. Т.2. Москва, Мир, 1982, 736 p.
[3] Gao G. Statistical modeling of SAR images: A survey. Sensors, 2010, vol. 1, iss. 1, pp. 775–795.
[4] Kupryashkin I. F., Likhachev V. P. Kosmicheskaya radiolokacionnaya s"emka zemnoj poverhnosti v usloviyah pomekh [Space radar survey of the Earth's surface under interference conditions]. Voronezh, Nauchnaya kniga Publ., 2014, 458 p.
[5] Korolev V.Yu. EM-algoritm, ego modifikacii i primenenie k zadache raz-deleniya smesej veroyatnostnyh raspredelenij [EM-algorithm, its modifications and application to the problem of separation of mixtures of probability distributions]. Moscow, IPI RAS Publ., 2007, 102 p.
[6] Teicher H. Identifiability of finite mixtures. The Annals of Mathematical Statistics, 1963, vol. 34, no. 4. pp. 1265 –1269.
[7] Prakasa Rao B.L.S. Characterizations of probability distributions through Q-independence. Theory of Probability and its Applications, 2018, vol. 62, iss. 2, pp. 335–338.
[8] Bolshev L.N., Smirnov N.V. Tablicy matematicheskoj statistiki [Tables of mathematical statistics]. Moscow, Nauka Publ., 1965, 464 p.
[9] Ayvazyan S.A., Bukhstaber V.M., Enyukov I.S., Meshalkin L.D. Prikladnaya statistika. Klassifikaciya i snizhenie razmernosti: sprav. izd. [Applied statistics. Classification and dimension reduction: reference ed.]. Moscow, Finansy i statistika Publ., 1989, 606 p.
[10] Wikipedia. The Free Encyclopedia. Expectation–maximization algorithm [Electronic resource]. Access mode: https://en.wikipedia.org/wiki/Expectation_maximization_algorithm (accessed: 26.10.2020).
[11] Wikipedia. The Free Encyclopedia. k-means clustering [Electronic resource]. Access mode: https://en.wikipedia.org/wiki/K-means_clustering (accessed: 30.10.2020).
[12] Korolev V.Yu., Nazarov A.L. Separating mixtures of probability distributions with the grid method of moments and the grid maximal likelihood method. Automation and Remote Control, 2010, iss. 71, pp. 455–472.
Достовалова А.М. Применение модели смеси вероятностных распределений в обработке радиолокационных изображений. Математическое моделирование и численные методы, 2020, № 3, с. 117–130.
Download article
Количество скачиваний: 855