Comparative positioning of ships on the basis of neural processing of digital images

• Autorzy: Stateczny A.
• Konferencja: Geodetic and Geodynamic Programmes of the CEI (Central European Initiative) (6-11.04.2003; Nice, France)
• Języki publikacji: EN

Abstrakty

EN

Satellite and radar systems have been the main information sources in marine navigation in recent years. Apart from commonly known anti-collision functions, the marine navigational radar constitutes the basis for a future comparative system of ship positioning. The sonar is an additional source of image information in the system. In this way, the data are derived from observing the surroundings of the ship's total measuring area. The system of comparative navigation is an attractive alternative to satellite navigation due to its autonomy and independence from external appliances. The methods of analytic comparison of digitally recorded images applied so far are based on complex and time-consuming calculation algorithms. A new approach in comparative navigation is the application of artificial neural networks for plotting the ship's position. In the positioning process, previously registered images can be made use of, as wen as their positions plotted for instance by means of the GPS system or by geodetic metbods. The teaching sequence is constituted by the registered images correlated with positions; it is performed earlier and can last for any length of time. After the process of teaching the network is completed, the dynamically registered images are put on the network input as they come, and a position interpolation is performed based on images recognized as closest to the image analyzed. A merit of this method is teaching the network with real images, along with their disturbances and distortions. The teaching sequence includes images analogous to those that will be used in practice. During the system' s working the response of the network (plotting the ship's position) is almost immediate. A basic problem of this method is the need for previous registration of numerous real images in various hydrometeorological conditions. The registered images should be subjected to digital processing, to the compression process in particular. One of the processing methods is encoding the image by means of projection method, and next giving the encoded vector to the input of GRNN (General Regression Neural Networks). The article presents a method of processing the image through encoding by projection method and interpolating the ship's position by GRNN network.

Słowa kluczowe

EN

radar; sonars; satellite navigation

• Wydawca: Wydział Geodezji i Kartografii Politechniki Warszawskiej
• Czasopismo: Reports on Geodesy
• Rocznik: 2003
• Tom: z. 1/64
• Strony: 295--301
• Opis fizyczny: Bibliogr. 11 poz., schem., rys.

Twórcy

autor

Stateczny A.

• The Institute of Marina Traffic Engineering, Maritime University Szczecin

Bibliografia

• 1. Austin G. L., Bellon A., Ballantyne E., Sea Trials of a Navigation System Based on Computer Processing of Marine Radar Images. The Journal of Navigation 1987 Vol. 40.
• 2. Austin G. L., Bellon A., Riley M., Ballantyne E., Navigation by Computer Processing of Marine Radar Images. The Journal of Navigation 1985 No 3.
• 3. Hayashi S., Kuwajima S., Sotooka K., Yamazaki H., Murase H., A Stranding Avoidance System Using Radar Image Matching - Development and Experiment. The Journal of Navigation May 1991 Vol. 44 No 2.
• 4. Specht D. F., A General Regression Neural Network, lEEE Transactions on Neural Networks, 1991 Vol. 2. No. 6.
• 5. Stateczny A., A Comparative System Concept of Plotting the Ship's Position. Proceedings of International Conference on Marine Navigation and Technology "MELAHA 2000" Alexandria Egypt 2002.
• 6. Stateczny A., Comparative Navigation; Gdańsk Scientific Society Gdańsk 2001. (in Polish)
• 7. Stateczny A., Methods of comparative plotting of the ship's position. Marine Engineering and Ports III. Editors C.A. Brebbia & J. Olivella. WIT Press Southampton, Boston 2002.
• 8. Stateczny A., Praczyk T., Artificial Neural Networks for Maritime Target Recognition. Gdańsk Scientific Society Gdańsk 2002. (in Polish)
• 9. Stateczny A., Problems of comparative plotting of the ship's position. Proceedings of the European Geophysical Society Symposium G9 "Geodetic and Geodynamic Programmes of the CEJ (Central European Initiative)" Nice 2002. Reports on Geodesy No. 1 (61), 2002.
• 10. Stateczny A., Problems of Computer Vessel Position Plotting by Comparative Methods. Science Work of Naval Academy Gdynia 1990 No 107A. (in Polish)
• 11. Stateczny A., Wąż M., Neural Algorithm of Fixing the Ship's Position. Annual of Navigation 2000 No. 2.