Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) Secure processing of visual information in the automated optoelectronic system of ground-space monitoring Dmitry Lovtsov Dmitry Gavrilov Grigory Makarenko Lebedev Institute of Precise Lebedev Institute of Precise FSI SCLI attachet to the Ministry Mechanics and Computer Mechanics and Computer of Justice of Russia Engineering (IPMCE) Engineering (IPMCE) Moscow, Russia Moscow, Russia Moscow, Russia Intell2019@yandex.com dal-1206@mail.ru gavrilov.da@mipt.ru Abstract: The main approaches to the development of an II. CONCEPTUAL-LOGICAL MODEL AND MAIN TASKS OF automated optoelectronic system of ground-space monitoring, AOES GSM providing secure processing of visual information under conditions of information competition, are considered. The The well-known invariant functional structure can be used as achievements have theoretical and practical value when solving a conceptual-logical model of AOES GSM (Fig. 1) [1,2]. the problem of information performance provision in different This structure is presented as a complex of functional areas of interests demanding visual information processing. subsystems: measurement (P1), observation (P2), identification Keywords: protected processing of privileged visual information; (P3), management decision-making (P4), centralized efficiency; accuracy; information competition coordination (P5), information exchange (P6) and information protection (P7) required for functioning under the conditions of I. INTRODUCTION information competition and ensuring the necessary protection Global informatization and information competition in the course of information processing. stipulate for introduction of a rational methodology of building efficient automated optoelectronic system of ground-space monitoring (AOES GSM) having high values of accuracy, promptness, reliability, stability, survivability, as well as a high degree of information security to ensure functioning in an aggressive information environment. One of the central problems in the field of automated image processing is ensuring high precision of solving specific tasks resistant to various detrimental aggressive factors, with a clearly defined and studied range of application. The development of the effective AOES seems possible through the use of a problem-oriented version of the integrated ICSD-approach (“informational-cybernetic-synergetic- Figure 1. Conceptual-logical model AOES GSM didactic”) [1], i.e. a systematic approach with emphasis on its The object of management (P0) receives various input informational, cybernetic, synergetic and didactic aspects, actions at time t: functional R(t), external target X(t) and external which consists in integrating the methodology of the coordinating X'(t), for which corresponding responses Q(t), Y(t), informational approach (when the object is considered as a goal- Y’(t) are formed. oriented information system), the methodology of the cybernetic approach (when the object is considered as a control system at The main tasks of AOES GSM are stabilization, detection, the level of information processes and information base localization and classification of objects of interest in photo and functioning algorithms) with the methodology of the synergetic video data in relation to various background-target situations. approach (when the object is considered as a dynamic self- Difficulties in solving these problems arise due to the following: organizing system that interacts with the environment) and the information losses when projecting a 3D scene (exposition) onto methodology of the didactic approach (when the object is the image plane; presence of noise in the image; changes in the considered as a system capable of self-learning) as part of the scene exposition; complex shapes of objects; changes in the methodology of the system approach (when the object is object shape; partial or complete overlaps and obturations of considered as a complex multi-level and multi-aspect system). scene objects; complex path of object motion; object goes beyond the frame boundaries or appears in the frame; relative 40 motion of the camera; real-time processing requirements etc. I(x,y) [2,3]. The tasks of AOES GSM are distributed as follows according to functional subsystems: ensuring stabilization of AOES GSM video images - subsystem P1 [4]; detection, localization and R{rs B, n, δ, x, φ, Hr, Нef, β} tracking - P2 [5]; classification and selection - P3 [6,7]; formation Stabilization of the visual flow of control actions - P4; design of learning samples and Q={QDLK, QIE, Qа} adjustment of system methods - P5 [8]; dynamic range V{σR, σA, σsh} compression and signal transmission [9] - P6; crypto-conversion of signals - P7. III. REORGANIZATION AND MAPPING OF MULTILEVEL AOES GSM ON THE CONCEPTUAL-LOGICAL MODEL The reorganization scheme and mapping of the multilevel P{d, k, ρ} AOES GSM on the conceptual-logical model is presented in Fig. 2. D{ω} Reorganization levels are characterized as follows: Learning of neural Prompt processing of visual Level 1. The choice of an 𝑚 ∈ 𝑀action method (technique) networks information c IE а from the set M of possible methods according to algorithm A. Q={Q , Q , Q } Q={Qc, QDLK, QIE} А: 𝑚 ∈ 𝑀. Evaluation of information efficiency and functional diagnostics The main subsystems operating at this level are the measurement subsystem (P1) and the coordination subsystem (P5). Q={Qc, QDLK, QIE, Qа} (Hн-H(Q*))=max) Level 2. Adaptation and modification of methods for solving Fig. 2 Reorganization scheme and mapping of the problems under conditions of informational competition. An multilevel AOES GSM on the conceptual-logical model effective algorithm A for choosing a method of action is formed in the result of learning in actual conditions and the narrowing Outputs operator G defines a rule for displaying a set of X of the set of uncertainty H. elements at the input to the set Y of output results for a 𝑚 ∈ 𝑀given method of action selected from the set M under Н → 0, А = 𝐹{𝐺, 𝐾}. conditions of uncertainty H. The main subsystem functioning at this level is the G: X × M × H → Y. information exchange subsystem (P6). The operator K evaluating the quality of the method of action Level 3. The self-organization and selection of a strategic determines the rule for displaying the set Y of output results for model is carried out on the basis of justification and assignment a 𝑚 ∈ 𝑀given method of action selected from the set M into the of the current operators G of outputs K, assessment of the quality set of quantities R associated with the characteristics of the of the action method, corresponding to the main goal S(t). system operation quality К: M × Y → 𝑅. The main subsystems operating at this level are the observation subsystem (P2) and the identification subsystem (P3). Level 4. Administrative management, decision making based on the received analytical information. The main subsystem functioning at this level is the decision making subsystem (P4). At the same time, the required degree of security and safety of information arrays is supported by the information protection subsystem (P7) continuously at all levels. Information security includes ensuring the reliability (noise immunity and noise proof features), confidentiality (secrecy, accessibility and imitation resistance), safeguarding (integrity, availability) of privileged visual information. Thus, information security consists in the ability to prevent accidental or deliberate distortion or destruction, disclosure or modification of information arrays in the information base [10]. 41 IV. ENSURING INFORMATION EFFICIENCY AND SECURITY OF Target characteristic: Safety Кef  max AOES GSM IN THE CONDITIONS OF INFORMATION Quality COMPETITION Accuracy Promptness factor Stability Survivability КA Кpr Кstab Кsurv КQ One of the main requirements for developing the effective Validity of Functioning Manageabilit decision- under fault AOES GSM is to ensure the quality of processing of meaningful Reliability Speed Timeliness making conditions Stability y Adaptability Continuity visual information received at the system input in the form of an Performance indicator Кef = Σλif(КA, Кpr, КQ, Кstab, Кsurv)  max information flow. System general technical requirements for information algorithmic support When developing an effective AOES GSM, the most Invariance to a Promptness of important task is to determine the quality indicators of methods Multi-level solutions class of solved problems Effective use of technical figures Statistical indicators Compatibility information security (Fig. 3). Assessment of AOES GSM efficiency The quality of information processing can be characterized by a combination of properties that determine the degree of its Functional diagnostics Reliability compliance with the goals of processing. In the general case, one Methods Implementations Hardware Statistical indicators Time indicators can distinguish internal quality indicators that characterize the Ensuring the required efficiency: Кef  max system content richness and external quality indicators that determine the security of the system [11, 12,13]. Figure 3. Ensuring efficiency of AOES GSM in the Internal quality indicators are responsible for such properties conditions of information competition of information processing as materiality - a property of The process of processing visual information covers a wide information that allows you to maintain value over time and range of methods with various applications. A certain set of includes indicators of completeness, ensuring rationality of methods is distinguished among the variety of the same in order management, and relevance, responsible for compliance with to develop algorithms for solving specific tasks. the dynamic state of objects, as well as cumulativity - a property that allows reflecting reality in a small informational array and In the general case, the technological process of processing includes selectivity indicators providing the qualification choice the visual information flow is a series of sequential actions of a limited number of information units from a large-volume aimed at analyzing information and bringing it to the desired informational array, and homoformism, which allow form at the system output. All the steps for processing visual aggregating large informational arrays into a small number of information, as a rule, are a sequential removal of non- informational units [14, 15]. informative components from the image and the selection of informative ones to solve the tasks. The following three main External quality indicators provide confidentiality properties technological operations can be distinguished in the for the reliability and safeguarding of information. The technological process of processing the input information flow. confidentiality property determines the status of the information The first one is reception, including the processes of formation external availability and is characterized by accessibility and registration of images, as well as their preliminary indicators (determining the degree of differentiation in the use compression and restoration. The second one is the of information arrays), secrecy (consisting in the ability to interpretation resulting in intellectual processing, generalization withstand the disclosure of the information meaning), imitation of the received data, control and decision making.The third one resistance (determining the degree of information protection is the communication operation responsible for receiving and from implementation and consisting in the ability to prevent transmitting information flow. The main operations, in turn, disinformation from entering the system). include various subprocesses that allow to form, register, The reliability property characterizes the degree of compress and restore images, summarize information obtained correspondence of real information units to their true value and as a result of intellectual processing and make management is determined by the parameters of noise immunity and noise decisions based on the same, as well as transmit and save proof features. The safeguarding feature is the possibility of information. targeted use of visual information arrays and the ability to In order to ensure security, partially processed visual prevent violation of the integrity of information arrays during information containing certain data necessary to ensure further the system operation. restoration of full significance is transmitted to the communication operation instead of the general array of visual data. For example, in case of using neural network methods of decoding visual information, learning samples are generated, and the weights of the neural network obtained in the process of learning are transmitted for further work through the information channel instead of arrays of learning images. The main characteristics affecting the efficiency and safety of AOES GSM are indicators of information accuracy KA, promptness Kpr, Q-factor KQ, stability Kstab, survivability of Ksurv, each of them corresponding to a certain importance indicators 0 ≤ 𝜆𝑖 ≤ 1 ∑ 𝜆𝑖 = 1, , i = 1, ..., 5. The main qualities 42 of these characteristics are the maximum use of the potential [6] Skobtsov V.Yu., Kruglikov S.V., Kim D.S., Novoselova N.A., Arkhipov capabilities of AOES GSM. Information security of AOES GSM V.I., Kulbak L.I., Nikolaenya E.D., Lapitskaya N.V., Vakulchik E .N., Saksonov R.V. Analysis of reliability, survivability and telemetry is defined as a function of private performance indicators indicators of onboard equipment of small spacecrafts // Cybersecurity issues. 2018. –No.4 (28) –Pp.54-69, DOI: 10.21681/2311-3456-2018-4- Кef=Σ𝜆i f(КA, Кpr, КQ, Кstab, Кsurv) max. 54-69. V. CONCLUSIONS [7] Gavrilov D.A. Quality assessment of objects detection and localization in а video stream // Bulletin of the MSTU named after N.E. Bauman. Ser. The main approaches to providing secure processing of Instrument manufacture. - 2019. –Vol. 2. - Pp. 40–55. visual information under conditions of informational [8] Gavrilov D.A. et al. Use of Neural Network Based Deep Learning competition in the automated optoelectronic ground-space Techniques for the Diagnostics of Skin Diseases // Biomed. Eng. (NY). – 2019. – vol. 52, –No. 5. –pp. 348–352. monitoring system are presented. [9] Gavrilov D.A. Pavlov A.V., Schelkunov D.N. Hardware implementation The considered proposals for ensuring secure processing of of dynamic range compression of digital images on FPGA Xilinx // information in AOES GSM are of theoretical and applied Journal of Radio Electronics. 2018. –No. 10. - DOI 10.30898 / 1684- 1719.2018.10.6, http://jre.cplire.ru/jre/oct18/6/text.pdf. importance in solving the problems of developing effective automated optoelectronic systems of special (intersectoral, etc.) [10] Gavrilov D.A., Pavlov A.V. Stream hardware implementation of the SURF algorithm // Bulletin of universities. Electronics. –2018. –Vol. 23.– designation, providing processing of multi-aspect visual No. 5. – Pp.502-511, DOI: 10.24151/1561-5405-2018-23-5-502-511. information. They can significantly increase the efficiency of [11] Schelkunov N.N., Gavrilov D.A., Fortunatov A.A. A system for testing using existing methods and tools for detection, localization and video stabilization algorithms operating in real time // Bulletin of the classification of images and, as a result, improve the quality of MSTU named after N.E. Bauman. Ser. Instrument manufacture. –2018. – visual information recognition, ensure the confidentiality of No. 4. – Pp. 112–126, DOI: 10.18698/0236-3933-2018-4-112-126. information processing, and also increase the safeguarding and [12] Pun A.B., Gavrilov D.A., Schelkunov N.N., Fortunatov A.A. Adaptive reliability of situation assessment under conditions of intense binarization algorithm for objects in a video sequence in real time // Achievements of Modern Radioelectronics. - 2018. –No. 9. - Pp. 40–48, information competition and continuously changing DOI 10.18127 / j20700784–201809–05. environment. [13] Gavrilov D.A., Melerzanov A.V., Asadov A.E., Zharov V.P. Secondary prevention and control of melanoma therapy using telemedicine REFERENCES technologies and standardized data processing // Problems of [1] Kosyanchuk V.V., Selvesyuk N.I., Zybin E.Yu., Khammatov R.R., standardization in healthcare. 2018. - No. 7–8. -Pp. 45–54 Karpenko S.S. The concept of ensuring information security of aircraft DOI.org/10.26347/1607-2502201807-08045-054. avionics // Cybersecurity issues. 2018. - No. 4 (28). - Pp. 9-20, DOI: [14] Lovtsov D. A., Loban A. V. An Effective New Technology for the 10.21681/2311-3456-2018-4-9-20. Distributed Processing of Measurement Data by S/C Automated Control [2] Kozachok A.V. Specification of a model for managing access to multi- System// Solar System Research, –2015, –Vol. 49, –No. 7, pp. 614–620, category resources of computer systems // Cybersecurity issues. 2018. - DOI: 10.1134/S0038094615070151. No. 4 (28) - Pp. 2-8, DOI: 10.21681/2311-3456-2018-4-2-8. [15] Lovtsov D. A., Karpov D. S. Dynamic Planning of Navigation [3] Deundyak V.M., Mogilevskaya N.S. Persistence of a polynomial scheme Determinations of Airspace and Missile Objects in an Automated Flight of split transmission of confidential data // Cybersecurity issues. 2018. - Test Control System// Solar System Research, 2011, Vol. 45, No. 7, pp. No. 4 (28). - Pp. 38–45. DOI: 10.21681/2311-3456-2018-4-38-45 645–651, DOI: 10.1134/S003809461107015X. [4] Maximov R.V., Krupenin A.V., Sharifullin S.R., Sokolovsky S.P. [16] Lovtsov D.A. Development of the information sphere of social production Innovative development of tools and technologies to ensure the Russian activities: achievements, security threats and legal regulation // State and information security and core protective guidelines // Cybersecurity law in the new information reality. 2018. –No.1. DOI: issues. –2019. – No.1(29). – Pp.10-17, DOI: 10.21681/2311-3456-2019- 10.31249/pras/2018.01.01. 1-10-17. [17] Preobrazhensky N.B., Kholopov Yu.A., Gavrilov D.A. Effective [5] Gavrilov, D.A., Mestetsky, L.M., Semenov A.B. A method for marking implementation and control of time intervals in specialized digital systems aircraft images in aerospace pictures based on continuous morphological // Journal of Radio Electronics –2019. –No.9. DOI: 10.30898/1684- models // Programming. –2019. - No. 6. –Pp.3-12, 1719.2019.8.12 DOI: 10.1134/S0132347419060025 [18] Melersanov A.V., Gavrilov D, A. Diagnosis of skin melanoma using convolutional neural networks of deep learning // Doctor –2018. –Vol. 29, No. 6. –Pp. 31-11. DOI: 10.29296/25877305-2018-06-06. 43