Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Zeszyty Naukowe / Akademia Morska w Szczecinie

2 2012

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: radar target tracking

Sortuj według:

Ogranicz wyniki do:

The analysis of methods of interaction between elementary filters in multiple model tracking filter in marine radars

Kazimierski W.

Zeszyty Naukowe / Akademia Morska w Szczecinie

2012

nr 32 (104) z. 2

81-87

Radar target tracking on a sea-going ship is a basic source of information about movement of other vessels, influencing directly safety of navigation. The research on improving of tracking methods has led to a new concept of multiple model neural filtration, which is a combination of multiple model approach with the use of artificial neural networks for the needs of estimation of movement vector. One of the key issue during designing of filter id to establish rules of interaction between elementary filters. The paper presents the most popular methods of manoeuvre detection and interaction of elementary filters in the numerical filtration. The modifications of them for the needs of neural tracking are proposed. Additionally, a concept of use of probabilistic neural network for this purpose is described. The idea was checked in the experimental research with the use of simulation. The result of the research confirmed usefulness of using PNN in multiple model filtration, showing however simultaneously the directions of future research in this. The research was financed by Polish National Centre of Science under the research project “Development of radar target tracking methods of floating targets with the use of multiple model neural filtering”.

Software implementation of multiple model neural filter for radar target tracking

Kazimierski W., Wawrzyniak N.

Zeszyty Naukowe / Akademia Morska w Szczecinie

2012

nr 32 (104) z. 2

88-93

The paper presents a software implementation of multiple model neural filter for radar target tracking. Such a filter may be proposed as an interesting alternative for numerical filters. The main purpose of software implementation is to provide a tool for complex research of the filter possibilities and adjusting options. A concept of a filter is briefly mentioned, however the main body of paper is focused on user-approach detailed description of application with UML use-case diagrams. Examples of detailed presentation of usecases are given and the general use-case diagram for application is included. The application itself is to be an advanced tool for researchers interested in analyzing target tracking process, providing different tracking methods and the possibility of adjusting their parameters. The possibility of simulating any scenario, as well as working with real data (also on-line) was ensured. The research was financed by Polish National Centre of Science under the research project “Development of radar target tracking methods of floating targets with the use of multiple model neural filtering”.