Abstract
In the present chapter, the problems of multidimensional images and image sequences representation and processing within the framework of the Earth remote sensing problems solving are considered. The issues of correlated data multidimensional arrays description and optimal and suboptimal processing thereof based on formalized mathematical models are investigated. It is proposed to use doubly stochastic autoregressive models as the basis for such models. It is shown that similar models enable to describe two essential properties of the actual satellite material. Firstly, the construction of doubly stochastic models allows for description of multidimensional random fields and time sequences thereof. This is of fundamental importance for real-time sequences of multispectral images each being considered as brightness values 3D array composed of separate two-dimensional frames, which correspond to the Earth surface registration results in a separate spectral band. A time sequence of such images is equivalent to four-dimensional random field with one-dimension corresponding to discrete time. Secondly, doubly stochastic models enable to carry out estimation of spatially heterogeneous images, i.e. images having probabilistic properties, which vary with spatial coordinates. Such variations are typical for actual satellite snapshots containing objects of various nature: rivers, forests, fields, etc. The chapter contains investigation of probabilistic and correlation properties of doubly stochastic models. Algorithms for these models parameters estimation based on actual satellite signals observations are proposed. It is shown that basing on the proposed models it is possible to synthesize multidimensional images filtering algorithms allowing for spatial heterogeneity of the images. Several classes of such algorithms enabling also to carry out processing of real-time sequences of multispectral satellite images are proposed. It has been established that the found algorithms possess higher effectiveness in comparison with known analogues. In this study, the problem of extended objects detection against the background of multispectral images time sequences is considered. A family of detection algorithms based on preliminary nonlinear filtering of these images is synthesized. Application of the developed algorithms, when solving problems of satellite images classification and natural or man-made objects monitoring, is briefly considered.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gonzalez R.C., Woods R.E.: Digital Image Processing, 4th edn, Pearson Education (2017)
LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521(7553), 436–444 (2015)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolution network. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision – ECCV 2014: 13th European Conference, Zurich, Switzerland, Proceedings, Part I, LNCS, vol. 8689, pp. 818–833. Springer International Publishing, NY (2014)
Bouman C.A.: Model Based Imaging Processing. Purdue University (2013)
Dudgeon, D.E., Mersereau, R.M.: Multidimensional Digital Signal Processing. Signal Processing Series. Prentice-Hall, Englewood Cliffs, New York (1984)
Krasheninnikov, V.R., Vasil’ev, K.K.: Multidimensional image models and processing. In: Favorskaya, M., Jain, L.C. (eds.) Computer Vision in Control Systems-3, ISRL, vol. 135, pp. 11–64. Springer International Publishing, Switzerland (2018)
Vasil’ev, K.K., Krasheninnikov, V.R.: Statistical analysis of multidimensional images sequences. Moscow: Radiotechnics (in Russian) (2017)
Vasil’ev, K.K., Dement’ev, V.E., Andriyanov, N.A.: Representation and processing of multispectral satellite images and sequences. Procedia Comput. Sci. 126, 49–58 (2018)
Vasil’ev, K.K., Dement’ev, V.E., Luchkov, N.V.: Analysis of efficiency of detecting extended signals on multidimensional grids. Pattern Recognit. Image Anal. 22(2), 400–408 (2012)
Shalygin, A.S., Palagin, Y.I.: Applied Methods of Statistical Modeling. Mashinostroenie, Mechanical Engineering Leningrad (1986)
Woods, J.W.: Two-dimensional Kalman filtering. In: Huang, T.S. (ed.) Two-Dimensional Digital Signal Processing I: Linear Filters. TAP, vol. 42, pp. 155–205. Springer, Berlin, Heidelberg, New York (1981)
Soifer, V.A. (ed.): Computer Image processing. Part I: Basic Concepts and Theory. VDM Verlag Dr. Muller E.K. (2009)
Jensen, J.: Introductory Digital Image Processing: A Remote Sensing Perspective. 4th edn. Pearson Education (2001)
Paliy, D., Foi, A., Bilcu, R., Katkovnik, V.: Denoising and interpolation of noisy Bayer data with adaptive cross-color filters. In:Â SPIE-IS&T Electronic Imaging (2007)
Zharrg, X.-P., Desai, M. D.: Adaptive denoising based on SURE risk. EEE Signal Pгocess. Lett. 10, 265–26 (1998)
Belyaeva O.V., Paschenko O.B., Filippov M.V.: Fast bilateral filtering of aerial photographs based on parallel decomposition into spatial filters. Math. Softw. Provis. Comput., Comput. Syst. Netw. 94, 1–8 (in Russian) (2017)
Favorskaya, M.N., Levtin, K.: Early smoke detection in outdoor space by spatio-temporal clustering using a single video camera. In: Tweedale, J.W., Jain, L.C. (eds.) Recent Advances in Knowledge-based Paradigms and Applications. AISC, vol. 234, pp. 43–56. Springer International Publishing Switzerland (2014)
Jähne, B.: Digital Image Processing, 6th edn. Springer, Berlin, Heidelberg (2005)
York Pratt, W.K.: Digital Image Processing. PIKS inside. 3rd edn. Wiley, New York (2001)
Favorskaya, M., Jain, L.C., Buryachenko, V.: Digital video stabilization in static and dynamic scenes. In: Favorskaya, M.N., Jain, L.C. (eds.) Computer Vision in Control Systems-1, ISRL, vol. 73, pp. 261–309. Springer International Publishing, Switzerland (2015)
Krasheninnikov, V.R.: Correlation analysis and synthesis of random field wave models. Pattern Recognit. Image Anal. 25(1), 41–46 (2015)
Gimel’farb, G.L.: Image Textures And Gibbs Random Fields. Springer, Berlin (1999)
Favorskaya, M.N., Jain, L.C., Savchina, E.I.: Perceptually tuned watermarking using non-subsampled shearlet transform. In: Favorskaya, M.N., Jain, L.C. (eds.) Computer Vision in Control Systems-4, ISRL, vol. 136, pp. 41–71. Springer International Publishing, Switzerland (2018)
Serra, J. (ed.): Image Analysis and Mathematical Morphology, vol. 2: Theoretical Advances. Academic Press, London (1988)
Vizilter, Y.V., Pyt’ev, Y.P., Chulichkov, A.I., Mestetskiy, L.M.: Morphological image analysis for computer vision applications. In: Favorskaya, M.N., Jain, L.C. (eds.) Computer Vision in Control Systems-1, ISRL, vol. 73, pp. 9–58. Springer International Publishing, Switzerland (2015)
Vasil’ev, K.K., Dement’ev, V.E., Andriyanov, N.A.: Doubly stochastic models of images. Pattern Recognit. Image Anal. 25(1), 105–110 (2015)
Vasil’ev, K.K., Dement’ev, V.E., Andriyanov, N.A.: Application of mixed models for solving the problem on restoring and estimating image parameters. Pattern Recognit. Image Anal. 26(1), 240–247 (2016)
Vasil’ev, K.K., Dement’ev, V.E., Andriyanov, N.A.: Filtration and restoration of satellite images using doubly stochastic random fields. CEUR Work. Proc. 1814, 10–20 (2018)
Vasil’ev, K.K., Dement’ev, V.E., Andriyanov, N.A.: Development of the filtering algorithm for doubly stochastic images based on models with multiple roots of characteristic equations. In: International Conference on Pattern Recognition and Artificial Intelligence, pp. 643–647 (2018)
Dement’ev, V.E., Andriyanov, N.A.: Application of mixed models of random fields for the segmentation of satellite images. CEUR Work. Proc. 2210, 219–226 (2018)
Krasheninnikov, V.R., Subbotin, A.U.: Doubly stochastic models of cylindrical images. Radiotechnics 6, 5–8 (2018) (in Russian) (2018)
Krasheninnikov, V.R., Kuvayskova, Yu.E., Subbotin, A.U.: Autoregressive models of random fields on the circle. In: V International Conference on Information Technology and Nanotechnology, pp. 150–156 (in Russian) (2019)
Habibi, A.: Two-dimensional Bayesian estimate of images. Proc. IEEE 60(7), 878–883 (1972)
Acknowledgements
The reported study was funded by the Russian Fund for Basic Researches according to the research projects â„– 16-41-732041 and â„– 18-47-730009.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Dement’ev, V.E., Krasheninnikov, V.R., Vasil’ev, K.K. (2020). Representation and Processing of Spatially Heterogeneous Images and Image Sequences. In: Favorskaya, M., Jain, L. (eds) Computer Vision in Advanced Control Systems-5. Intelligent Systems Reference Library, vol 175. Springer, Cham. https://doi.org/10.1007/978-3-030-33795-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-33795-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33794-0
Online ISBN: 978-3-030-33795-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)