Recognition of aircrafts by optical system in real time

Computer engineering. Information technology


Аuthors

Mirzoyan A. S.1*, Malyshev O. V.1**, Khmarov I. М.2***, Kanivets V. Y.3****

1. Rybinsk State Aviation Technical University named after P.A. Soloviev, RSATU, 53, Pushkin St., Rybinsk, Yaroslavl region, 152934, Russia
2. Research center (Tver) of Central Research Airforce Institute of the Russian Defense Ministry, 32, Afanasy Nikitin emb., Tver, 170026, Russia
3. Air force academy named after professor N.E. Zhukovskii and Y.A. Gagarin, Voronezh, Russia

*e-mail: andr.s.mirzoyan@gmail.com
**e-mail: amspectre@gmail.com
***e-mail: khmarov314@mail.ru
****e-mail: martanvik@mail.ru

Abstract

Application field of the results of this research relates to the solution of the problem of aircraft recognition by optical systems to provide:

 - control of the air space by international missions at «hot spots»;
 - documentation of situations in the sky by military correspondents and witnesses, equipped with video techniques;
 - documentation of situations in the sky in border districts;
 - control of the air space by defense systems (also without using of radio channels) etc.

The aim of the work consists in determination of aircraft type by recognition system through its 2D image on photo-integrated matrix of visible, ultraviolet or infrared range in real time.

The proposed system of algorithms differs from its earlier developed counterparts mainly by recognition provision (with probability greater than 0.9) of 8 up to 12 types of military aircraft through their 2D dynamic optical images received by standard optical-electronic equipment and computing facilities.

Operating principle of the recognition system bases on the following principle. It singularizes an aircraft against the background of firmament with subsequent formation of its outer contour. Then the system compares this received real contour of aircraft image with reference contours of aircraft digital models from a given class stored in long-term memory. Reference contours herewith should be obtained at all possible aspect angles of digital models. Among all reference contours, the system must sel ect the one with minimum deviation fr om the real contour according to given matching metric. The basic means for time acceleration of aircraft recognition consist of algorithms with preprocessing and proper organization of long-term memory. Application of the introduced algorithm of real and reference images matching by Nikodims metric makes it possible to implement recognition of aircraft type in real time.

Working test of recognition system prototype hardware implementation on physical aircraft models and videotapes of real aircraft flights has shown high probability of correct recognition (0,92-0.98) with minimum time delays (40-280 ms).

In addition we have a possibility to solve the problem of correct recognition with probability 0,92-0.98 in practical formulation for 8-12 aircraft types using the following standard hardware capabilities:

  1. Optical system parameters: frame frequency 24 Hz, receiving matrix size 720×576 pixels.
  2. Computing device parameters: clock frequency 3 GHz, RAM 4 Gb, and LTM 256 Mb.

Keywords:

recognizing, aircrafts, air targets

References

  1. Vazhinskii V.N., Ivanova E.E., Teterin V.V. Opticheskii zhurnal, 1996, no. 8, pp. 37-42.
  2. Kazanskii N.L., Khmelev R.V. Kompyuternaya optika, 2000, no. 20, pp. 128-133.
  3. Maltsev G.N. Opticheskii zhurnal, 1998, no. 6, pp. 62-66.
  4. Shubnikov E.I. Opticheskii zhurnal, 1995, no. 4, pp. 19-25.
  5. Divin G.D. Opticheskii zhurnal, 1995, no. 9, pp. 12-17.
  6. Morris H., De Pass M.M. Target Classifications using Scale Spaces. Proc. of SPIE, 2006, vol. 6239, pp. 623904 (1-9).
  7. Ma L., Vong M-A.Q., Abousleman G.P., Si J. Automatic-Target-Recognition-Assisted Image Coding. Proc. of SPIE, 2002, vol. 4726, pp. 203-213.
  8. Malyshev V.A., Khmarov I.M., Malyshev O.V., Kanivets V.Yu. Raspoznavanie nazemnykh ob«ektov i letatelnykh apparatov 2D i 3D optiko-elektronnymi sistemami (Recognition of ground targets and aircraft 2D and 3D opto-electronic systems), Мoscow, NTTs «Informtekhnika», 2013, 158 p.
  9. Malyshev O.V., Khmarov I.M., Kondrashov N.G. Vestnik Moskovskogo aviatsionnogo instituta, 2011, vol. 18, no. 1, pp. 142-149.
  10. Devit N., Driggers R., Voltmerhausen R., Mauror T. The Impact of Display Artifacts on Target Identification. Infrared and Passive Millimeter-wave Imaging Systems: Design, Analysis, Modeling, and Testing. Proc. of SPIE, 2002, vol. 4719, pp. 24-33.
  11. Mirzoyan A.S., Khmarov I.M., Kondrashov N.G., Shakhov S.V. Vestnik Moskovskogo aviatsionnogo instituta, 2013, vol. 20, no. 4, pp. 118-129.
  12. Malyshev O.V. Vestnik Rybinskoi gosudarstvennoi aviatsionnoi tekhnologicheskoi akademii im. P.A. Soloveva, 2011, no. 1(19), pp. 145-151.
  13. Skvortsov A.V. Vychislitelnye metody i programmirovanie, 2002, vol. 3, pp. 116-123.
  14. Mirzoyan A.S. Vestnik Rybinskogo gosudarstvennogo aviatsionnogo tekhnicheskogo universiteta im. P.A. Soloveva, 2013, no. 4 (27), pp. 17-23.
  15. Malyshev O.V., Khmarov I.M., Vishnyakov A.S., Kondrashov N.G. Vestnik Moskovskogo aviatsionnogo instituta, 2011, vol. 18, no. 4, pp. 93-102.
  16. Today I feel like, available at: http://www.todayifeellike.com/videos/f22.wmv

mai.ru — informational site of MAI

Copyright © 1994-2024 by MAI