Engineering Synthesis of Nonlinear Spatial Selection with Artificial Intelligence Elements to Suppress Critical Interference of Background in Aviation and Space-Based Opto-Electronic Devices

• Published in: Nauka i obrazovanie (Moskva) Vol. 15; no. 8; pp. 116 - 139
• Main Authors: Levshin, Viktor, Muratov, Konstantin
• Format: Journal Article
• Language: English; Russian
• Published: MGTU im. N.È. Baumana 03.08.2015
• Subjects: artificial visual intelligence; critical interference of background; filter-discriminator; nonlinear spatial selection; opto-electronic device; parametrically-stochastic approach; probabilistic recognition characteristics; topological characteristics
• ISSN: 1994-0408; 1994-0408
• DOI: 10.7463/0815.0789709

The previous authors’ works have shown that the system of quasi-optimal linear spatial filtering, due to the restriction of this class of filters, related to the superposition principle, has very limited capacity to suppress the most critical interference spatially inhomogeneous background. Such partial suppression does not meet extreme approach requirements for providing high probability characteristics to detect small targets in the most difficult background conditions.In this regard, there is a conclusion that it is necessary to find a different approach, in which the result of the system operation in complex background does not depend on the level of the background noise at the input. This article performs an engineering synthesis of the system with the artificial visual intelligence elements, which recognizes a class of the small-sized radiating objects with the suppression of the most critical interference through nonlinear topological selection.Consideration of this problem begins with the formation of the filter-discriminator aperture, which is a basis for this theory, «echoing» with the theory of optimal nonlinear filtering spatial Poisson processes. Thus, formation of the optimized nonlinear filter structure is based on the optimal linear filter (Wiener filter) structure. As a result, there are three versions of filter apertures (4-, 8- and 16-connected ones), with one of which later providing operations of the object shape discrimination. The focus of the article is, mainly, on the 8-connected aperture, as the average in balance of efficiency and complexity option.The article pays considerable attention to development of signs and algorithms to select the objects by size and shape. It shows that selection on a uniform background is possible by the maximum value of the first derivative and to separate the most critical form of Markov’s field inhomogeneities and background brightness, as the fragments of component boundaries of macrostructure background – edges («steps») and targets, you must use the anisotropy coefficients of the first and second order. The result of using the system, most effectively separating of signs, was the formation of the so-called «areas of selection».Mathematical models of the target and interference of parametrically-stochastic approach, as well as simulation on a semi-natural test frame with a fairly complex background «scene», proved the fundamental capability of the synthesized circuits to suppress radically the sources of interference signals, which are tens and even hundreds times greater than the signals from targets at the input. Thus, unlike the method based on optimal linear filtering, this approach allows the nonlinear «blockers» to suppress completely interference previously recognized by topological discriminators.Control sampling of points of the semi-natural frame enabled us to estimate conditional probabilities of a true solution of the target detection problem. The estimate has shown that the obtained probability of missing the target and false alarm are quite acceptable the values that make up a few percent.Obtained results show the incomparable advantages in complex background situation of presented non-linear method as compared to its traditional linear analogues.