|Article title||ALGORITHMS FOR AUTOMATED SELECTION OF THE AREA AS LANDING SITES, AND LANDING OF MANNED AND UNMANNED AERIAL VEHICLES ACCORDING TO THE ONBOARD OPTICAL-ELECTRONIC SYSTEM|
|Authors||V.A. Bondarenko, G.E. Kaplinskiy, S.N. Krjukov, V.A. Pavlova, V.A. Tupikov, P.K. Shulgenko|
|Section||SECTION VII. COMMUNICATION, NAVIGATION AND GUIDANCE|
|Month, Year||01-02, 2017 @en|
|Index UDC||623.746.-519 + 623.746.174|
|Abstract||This paper covers the task of landing site selection automation for safe unmanned and manned aerial vehicles landing. In the first part of this paper aThe method and algorithm for land-ing site selection is are proposed. The method is based on fusion of two stage analysis of aerial images from onboard optical system. First stage of algorithm consists of area height map recon-struction from a set of images taken from onboard optical system with use of stereoscopic effect in the process of straightforward carrier flight. The theoretical basis for the used area height map reconstruction approach is provided so as the results of successful application of the corresponding algorithm to real aerial imagery analysis. At second stage of the automatic landing site selection algorithm the texture analysis of the same area image is performed using the feedforward artificial neural network. A brief description of the artificial neural network architecture used is given and the results of aerial image texture analysis are shown. The second part of a paper describes an algorithm for artificially created reference point detection and recognition on images from onboard optical system of aerial vehicle and an algorithm for automatic landing onto the detected reference point. The test results of automatic landing algorithm onboard of flying laboratory based on the quadrotor are provided. As a result of conducted research the authors have developed a technology for making a computer vision system that carries the tasks of automatic landing site selection for landing the aerial vehicle at unknown terrain, task of relative three-dimensional positioning of aerial vehicle using the images of artificially created reference point and task of automatic AV landing onto the artificially created reference point. Based on helicopter type unmanned aerial vehicle a flying laboratory is developed and presented, equipped with electro-optical system and wireless communication system. Flying laboratory incorporates the algorithm of automatic search and recognition for artificially created reference point from real time imagery by UAV onboard optical system, and algorithm for automatic UAV landing at the detected reference point. The paper contains the field test results of the proposed system, which show its robustness and efficiency. The comparative analysis of proposed method with the other existing approaches for landing automation is provided.The test results of automatic landing algorithm onboard of flying laboratory based on the quadrotor are provided.|
|Keywords||Landing site selection automation; automatic UAV landing; stereogrammetry; texture anal-ysis; artificial neural network.|
|References||1. Gruzman I.S., Kirichuk V.S., Kosykh V.P., Peretyagin G.I., Spektor A.A. Tsifrovaya obrabotka izobrazheniy v informatsionnykh sistemakh: uchebnoe posobie [Digital image processing in information systems: a tutorial]. Novosibirsk: Izd-vo NGTU, 2002, 352 p.
2. Tsai R.Y. A versatile camera calibration technique for high-accuracy 3D machine vision me-trology using off-the-shelf TV cameras and lenses, IEEE Journal of Robotics and Automation RA-3(4), 1987, pp. 323-344.
3. Duda R., Hart P. Pattern Classification and Scene Analysis, John Wiley and Sons, 1973,
4. Garcia-Padro P. J., Sukhatme G.S., Montgomery J.F. Towards vision-based safe landing for an autonomous helicopter. Robotics and Autonomous Systems, 2000.
5. Hermansson J, Gising A, Skoglund M, Schön. Autonomous Landing of an Unmanned Aerial Vehicle, Technical Report, Automatic Control, Linkopings Universitet, Sweden, 2010.
6. Merz T., Duranti S., Conte G. Autonomous landing of an unmanned helicopter based on vision and inertial sensing, Experimental Robotics IX, Springer Tracts in Advanced Robotics, 2006, Vol. 21, pp. 343-352.
7. Tupikov V.A., Pavlova V.A., Kaplinskiy G.E., Kryukov S.N. Algoritm avtomaticheskoy posadki bespilotnogo letatel'nogo apparata vertoletnogo tipa s ispol'zovaniem bor-tovoy optiko-elektronnoy sistemy [The algorithm of automatic landing unmanned aerial vehicle helicopter-type using on-Board optical-electronic systems ], Izvestiya TulGU. Tekhnicheskie nauki [Izvestiya of the Tula state University. Engineering science], 2016, No. 11-3, pp. 86-95.
8. Bradley D., Roth G. Adaptive Threshholding Using Integral Image, Journal of Graphics Tools, Vol. 12, Issue 2, pp. 13-21.2007. NRC 48816.
9. Fukushima K., Miyake S. Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position, Pattern recognition, 1982, No. 15 (6), pp. 455-69.
10. Furman Ya.A., Yur'ev A.N., Yanshin V.V. Tsifrovye metody obrabotki i raspoznavaniya binarnykh izobrazheniy [Digital methods of processing and recognition of binary images]. Krasnoyarsk: Izd-vo Krasnoyarskogo universiteta, 1992, 248 p.
11. Krasil'nikov N.N. Tsifrovaya obrabotka 2D- i 3D-izobrazheniy: ucheb. posobie [Digital pro-cessing of 2D and 3D images: a tutorial]. St. Petersburg: BKhV-Peterburg, 2011, 608 p.
12. Baklitskiy V.K. Korrelyatsionno-ekstremal'nye metody navigatsii i navedeniya [Correlation-extreme methods of navigation and guidance]. Tver': TO «Knizhnyy klub», 2009, 360 p.
13. Alpatov B.A., Babayan P.V., Balashov O.E., Stepashkin A.I. Metody avtomaticheskogo obnaruzheniya i soprovozhdeniya ob"ektov. Obrabotka izobrazheniy i upravlenie [Methods for the automatic detection and tracking of objects. Image processing and management]. Moscow: Radiotekhnika, 2008, 176 p.
14. Shafait F., Keysers D., Breuel T.M. Efficient implementation of local adaptive thresholding tech-niques using integral images. Proc. SPIE vol. 6815, Document Recognition and Retrieval XV, 2008.
15. Sauvola J., Pietikainen M. Adaptive document image binarization, Pattern Recognition, 2000, No. 33, pp. 225-236.
16. Gonzalez R.C., Woods R.E. Digital Image Processing. 2nd edition, Prentice-Hall, 2002, 793 p.
17. Hu M.K. Visual Pattern Recognition by Moment Invariants, IRE Trans. Info. Theory, 1962, Vol. IT-8, pp. 179-187.
18. Crow F. Summed-area tables for texture mapping, In Proceedings of SIGGRAPH, 1984,
Vol. 18 (3), pp. 207-212.
19. Abubaker A., Qahwaji R., Ipson S., Saleh M. One Scan Connected Component Labeling Tech-nique, Signal Processing and Communications, 2007, pp. 1283-1286.
20. Schmidt W.F., Kraaijveld M.A., Duin R.P.W. Feedforward neural networks with random weights, Proc. of 11 th IAPR International Conference on Pattern Recognition Conference B: Pattern Recognition Methodology and Systems, 1992, Vol. II, pp. 1-4.
21. Yichuan Tang, Ruslan Salakhutdinov. Learning stochastic feedforward neural networks, Pro-ceedings of the 26th International Conference on Neural Information Processing Systems, 2013, pp. 530-538.