Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: intelligent navigation

Sortuj według:

Ogranicz wyniki do:

Ship recognition and tracking system for intelligent ship based on deep learning framework

Liu B., Wang S. Z., Xie Z. X., Zhao J. S., Li M. F.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

2019

Vol. 13. no. 4

699--705

Automatically recognizing and tracking dynamic targets on the sea is an important task for intelligent navigation, which is the prerequisite and foundation of the realization of autonomous ships. Nowadays, the radar is a typical perception system which is used to detect targets, but the radar echo cannot depict the target’s shape and appearance, which affects the decision-making ability of the ship collision avoidance. Therefore, visual perception system based on camera video is very useful for further supporting the autonomous ship navigational system. However, ship’s recognition and tracking has been a challenge task in the navigational application field due to the long distance detection and the ship itself motion. An effective and stable approach is required to resolve this problem. In this paper, a novel ship recognition and tracking system is proposed by using the deep learning framework. In this framework, the deep residual network and cross-layer jump connection policy are employed to extract the advanced ship features which help enhance the classification accuracy, thus improves the performance of the object recognition. Experimentally, the superiority of the proposed ship recognition and tracking system was confirmed by comparing it with state of-the-art algorithms on a large number of ship video datasets.

Calculation and measurement of tide height for the navigation of ship at high tide using artificial neural network

Li Q., Bing-Dong Y., Bi-Guang H.

Polish Maritime Research

2018

S 3

99--110

Accurate tide height is crucial for the safe navigation of large deep-draft ships when they enter and leave the port. We have proposed an accurate forecasting method for the tide heights from the observation data and neural networks, which can easily calculate the tidal window period of large deep-draft ships’ navigation through long channels at high tide. Moreover, an artificial neural network is established for the tide height from the observation of tide heights before their current time node. For an ideal forecast, the neural network was optimized for one year with the tide height data of Huanghua Port. In case of large ships, their tidal characteristics of channels for are complex. A new method is proposed for the observation of multiple stations and artificial neural networks of each observation station. When ships are navigating through the port, the tide height is predicted from the observed data and forecast tide heights of multiple observation stations. Thus, a valid tidal window period is secured when the ships enter the port. Comparative analysis of the ship’s tidal window period with that of the measured one can lead us to conclude that the forecasted data has a strong correlation with the measurement. So, our proposed algorithm can accurately predict the tide height and calculate the node timing when the ship enters and depart the port. Finally, these results can be applied for the safe navigation of large deep-draft ships when the port is at high tide.