To enhance remote sensing for maritime safety and security, various sensors need to be integrated into a centralized maritime surveillance system (MSS). High-frequency (HF) radar systems are a type of mainstream technology widely used in international marine remote sensing and have great potential to detect distant sea surface targets due to their over-the-horizon (OTH) capability. However, effectively recognizing targets in spectra with intrinsic strong disturbance echoes and random environmental noise is still challenging. To avoid the above problem, this paper proposes an adaptive signal identification method to detect target signals based on a rapid and flexible threshold. By integrating a watershed segmentation algorithm, the subsequent direction result can be used to automatically compute the direction of arrival (DOA) of the targets. To assist in the orientation of the object, forward intersections are integrated with the technique. Hence, the proposed technique can effectively recognize vessel echoes with automatic identification system (AIS) verification. Experiments have demonstrated the promising feasibility of the proposed method’s performance.

A network of high-frequency radars (HFRs) has been deployed around Taiwan. The wide-area data coverage is dedicated to revealing near real-time sea-surface current information. This paper investigates three primary objectives: (1) describing the seasonal current synoptic variability; (2) determining the influence of wind forcing; (3) describing the tidal current field pattern and variability. Sea surface currents derived from HFR data include both geostrophic components and wind-driven components. This study explored vector complex correlations between the HFR time series and wind, which was sufficient to identify high-frequency components, including an Ekman balance among the surface currents and wind. Regarding the characteristics of mesoscale events and the tidal field, a year-long high-resolution surface dataset was utilized to observe the current–eddy–tide interactions over four seasons. The harmonic analysis results derived from surface currents off of northeastern Taiwan during 2013 are presented. The results agree well with the tidal parameters estimated from tide-gauge station observations. The analysis shows that this region features a strong, mixed, mainly semidiurnal tide. Continued monitoring by a variety of sensors (e.g., satellite and HFR) would improve the understanding of the circulation in the region.

In previous research, the identification of the Bragg region, which is often achieved using image recognition, was easily affected by ionospheric interference and different manual parameter settings. Strong disturbances from the ionosphere and other environmental noise may interfere with high-frequency radar (HFR) systems when determining first-order Bragg regions and thus may directly influence the surface current mapping performance. To avoid human intervention in first-order Bragg-region recognition, deep learning methods were used to extract multiple levels of feature abstractions of the first-order Bragg region. In this study, to assist in developing sufficient training data, a procedure integrating a morphological approach and Otsu’s method was proposed to provide manual labelled data for a U-Net deep learning model. Additionally, several sets of activation functions and optimizers were used to achieve optimal deep learning model performance. The best combination of model parameters results in an accuracy of over 90%, an F1 score of over 80%, and an intersection over union (IoU) reaching 60%. The identification time of one image is approximately 70 ms. These results demonstrate that this deep learning model can predict the position of first-order Bragg regions under ionospheric interference and avoid being affected by strong noise that could cause prediction errors. Hence, deep learning and image fusion processing can effectively recognize the first-order Bragg regions under strong interference and noise and can thereby improve the surface current mapping accuracy.