Lade...
Journal Title
OCEANS 2023 - Limerick
2 Ergebnisse
Filter
Einstellungen
Gerade angezeigt 1 - 2 von 2
- Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Study on pulse form design for monostatic MIMO sonar systemsActive sonar systems typically consist of a transmitter (or transmitter array) and a receiver array and are known as a Single-Input-Multiple-Output (SIMO) system. A Multiple-Input-Multiple-Output (MIMO) sonar, on the other hand, uses multiple transmitters in order to emit different transmitter pulses into the same area. In a monostatic array, this allows the travel time information to be multiplied, resulting in high angular resolution at comparatively low hardware cost if the transmitter pulses can be separated from each other in the receive-side signal processing. This separation can be achieved by transmitting in different frequency or time windows, but this leads to a limited bandwidth or an increased overall ping period. In this paper, a method based on coding techniques and correlation filters are used for pulse separation, which means that the aforementioned limitations no longer apply. In doing so, this paper demonstrates various coding methods and the transmitted pulses generated by them for a monostatic MIMO sonar system. For comparison standard sonar pulses, such as linear frequency modulated (LFM), as well as hyperbolic frequency modulated (HFM) pulses are used as well. Furthermore, new approaches such as LFM sequences, LFM chains and orthogonal frequency division multiplexing are comparatively examined for the use of MIMO sonar systems.Wissenschaftlicher Artikel70 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Tackling data scarcity in sonar image classification with hybrid scattering neural networksData scarcity remains the main challenge when developing deep learning models for sonar image analysis. Although dataset augmentation with synthetically generated images has been proposed, these methods are far from optimal as they are unable to capture the range of physical factors affecting sonar images, given the small data regimes used for their training. This work focuses on an alternative solution and investigates the learning of suitable representations for classifying small-sized sonar datasets. To achieve this, we propose a new approach that entails the combination of convolutional and scattering neural networks, a wavelet-based neural network that produces feature map representations robust to image variations. Our experiments show that these representations are easier to classify, leading to a performance increase of 4.5 percentage points in F1-score for the combined network compared to a plain convolutional neural network. Furthermore, we interpret the representation obtained by the scattering transformation as robust feature descriptors, where the geometric shapes of underwater objects are rendered prominent and stable to minor sonar distortions.Wissenschaftlicher Artikel71