Article

Article title IMAGE ANALISYS TECHNOLOGY FOR AIRCRAFT TECHNICAL VISION SYSTEMS
Authors B.A. Alpatov, P.V. Babayan, O.E. Balashov, A.A. Barancev, A.B. Feldman
Section SECTION II. VISION SYSTEM AND ONBOARD COMPUTERS
Month, Year 02, 2016 @en
Index UDC 004.932.2
DOI
Abstract In this paper we propose a solution to ensure the aircraft safety by using of the technical vision system of aircraft. On board the aircraft mounted only one video sensor, which is source of image. To improve aircraft safety should be reduced situational uncertainty surrounding the aircraft. In the scientific and technical point of view to avoid collisions are required development of technical means for environment monitoring. The technology of image analysis allows automati- cally detect dangerous situations and avoid collisions. For the aircrafts the approach to other airplanes and birds, the approach to the surface of the earth, high buildings and power lines are dangerous situations. To improve safety through effective use of other aircraft systems this technology provides identification of air and ground objects and visual cues. Based on the analysis of the surrounding space around an aircraft is decided there is danger of collision, selected the most dangerous situation and predicted time to collision. Board vision system can warn the crew of the occurrence of a risk of collision, and give the location of important landmarks: the runway, control tower, power lines or completely control their environments and the movement of aircraft, such for driving on the optimal flight path. Detection and identification of ground objects and visual landmarks is made by comparing the video sensor data installed on board the aircraft, with the data of a digital elevation model and digital models of objects corresponding to the current navigation parameters. A detection of the power line on the images is made by using a modified Radon transform. To avoid collisions are necessary automatically detect aircrafts in the image sequence. The algorithm works in real time and effectively detect aerial objects in the image sequence even when the sizes of objects change rapidly, for example, when approaching. Detection of air objects occurs in several stages. The first step is a preliminary detection of candidate objects. The next stage is the confirmation of previous results and restore the object"s shape. To identify air objects are calculated handle external outline, by which is determined the aircraft class.

Download PDF

Keywords Image; machine vision; object detection; recognition; air safety; obstacle detection system.
References 1. Postanovlenie pravitel'stva RF № 138 ot 11 marta 2010 g. «Ob utverzhdenii fede-ral'nykh pravil ispol'zovaniya vozdushnogo prostranstva rossiyskoy federatsii» [Russian Federation Government Resolution № 138 dated March 11, 2010 "On approval of the federal rules of use of air space of the Russian Federation"].
2. Shibaev V. Shnyrev A., Bunya V. Bespilotnye aviatsionnye sistemy: bezopasnost' poletov i kriticheskie-faktory [Unmanned Aircraft Systems: flight safety and critical factors], Aerokosmicheskiy kur'er [Aerospace Courier], 2011, No. 1, pp. 55-58.
3. Aleshin B.S., Sukhanov V.L., Shibaev V.M. Obespechenie bezopasnosti poletov bespilotnykh aviatsionnykh sistem v edinom vozdushnom prostranstve [Ensuring the safety of unmanned aircraft systems in flight common aviation area], Trudy TsAGI [Proceedings CAGI], 2011, Vol. XLII, No. 6, pp. 73-83.
4. Nikiforova L.N., Yakovlev K.S. Malovysotnyy polet vertoleta i problemy ego avtomatizatsii [Low-altitude flight of the helicopter and its automation problems], Iskusstvennyy intellekt i prinyatie resheniy [Artificial intelligence and decision-making], 2009, No. 3, pp. 42-48.
5. Rukovodstvo po upravleniyu bezopasnost'yu poletov – IKAO, 2013 [Safety Management Manual – ICAO, 2013], 300 p.
6. Kanashchenkov A.I., Moybenko V.I., Karashchan S.V. Povyshenie kachestva radiolokatsionnoy informatsii pri malovysotnom polete [Increase radar data quality in low-altitude flight], Radiotekhnika [Radio engineering], 2009, No. 8, pp. 48-54.
7. Johnson E.N. et al. Flight testing of nap of-the-earth unmanned helicopter systems, 67th American Helicopter Society International Annual Forum, Virginia Beach, Virginia, 2011, pp. 3180-3192.
8. Alpatov B.A., Blokhin A.N., Kostyashkin L.N., Romanov Yu.N., Shapka S.V. Semeystvo mnogofunktsional'nykh sistem obrabotki videoizobrazheniy "Okhotnik" [The family of multi-function image processing system "Hunter"], Tsifrovaya obrabotka signalov [Digital signal processing], 2010, No. 4, pp. 44-51.
9. Bezdek J.C. Pattern Recognition with Fuzzy Objective Function Algorithms. New York: Plenum Press, 1981, 256 p.
10. Jain A., Murty M., Flynn P. Data clustering: A review, ACM Computing Surveys, 1999, Vol. 31, No. 3, pp. 264-323.
11. Alpatov B.A., Babayan P.V., Balashov O.E., Stepashkin A.I. Metody avtomaticheskogo obnaruzheniya i soprovozhdeniya ob"ektov. Obrabotka izobrazheniy i upravlenie [Methods of automatic detection and tracking of objects. Image Processing and Management]. Moscow: Radiotekhnika, 2008, 176 p.
12. Smith S.W. The Scientist and Engineer's Guide to Digital Signal Processing. California Technical Pub, 1997, 626 p.
13. Toft P.A. The Radon Transform: Theory and Implementation, PhD Thesis, Technical University of Denmark, 1996.
14. Candamo J., Kasturi R., Goldgof D. and Sarkar S. Detection of Thin Lines Using Low Quality Video from Low Altitude Aircraft in Urban Settings", IEEE Transactions on aerospace and electronic systems, July 2009, Vol. 45, No. 3.
15. Nussberger A. and others. Aerial Object Tracking from an Airborne Platform, International Conference on Unmanned Aircraft Systems (ICUAS), 2014, pp. 1284-1293.
16. Alpatov B.A., Blokhin A.N., Murav'ev V.S. Algoritm obrabotki izobrazheniy dlya sistem avtomaticheskogo soprovozhdeniya vozdushnykh ob"ektov [Image processing algorithm for automatic tracking systems of air objects], Tsifrovaya obrabotka signalov [Digital signal processing], 2010, No. 4, pp. 12-17.
17. Chan T.F., Vese L.A. A Multiphase level set framework for image segmentation using the Mumford and Shah model, International Journal of Computer Vision, 2002, Vol. 50 (3), pp. 271-293.
18. Kumar B.V.K.V., Mahalanobis A., Juday R.D. Correlation pattern recognition. Cambridge University Press, 2005, 402 p.
19. WongW.T., Shih F.Y. and Liu J. Shape-based image retrieval using support vector machines, Fourier descriptors and self-organizing maps, International Journal of Information Sciences, 2007, No. 177 (8), pp. 1878-1891.
20. Alpatov B.A., Babayan P.V., Smirnov S.A., Maslennikov E.A. Algoritm predvaritel'nogo otsenivaniya prostranstvennoy orientatsii ob"ekta s pomoshch'yu deskriptora vneshnego kontura [Prior estimation algorithm spatial orientation of the object via outer contour descriptor], Tsifrovaya obrabotka signalov [Digital signal processing], 2014, No. 3, pp. 43-46.

Comments are closed.