High-frequency surface wave radar (HFSWR) plays an important role in wide area monitoring of the marine target and the sea state. However, the detection ability of HFSWR is severely limited by the strong clutter and the interference, which are difficult to be detected due to many factors such as random occurrence and complex distribution characteristics. Hence the automatic detection of the clutter and interference is an important step towards extracting them. In this paper, an automatic clutter and interference detection method based on deep learning is proposed to improve the performance of HFSWR. Conventionally, the Range-Doppler (RD) spectrum image processing method requires the target feature extraction including feature design and preselection, which is not only complicated and time-consuming, but the quality of the designed features is bound up with the performance of the algorithm. By analyzing the features of the target, the clutter and the interference in RD spectrum images, a lightweight deep convolutional learning network is established based on a faster region-based convolutional neural networks (Faster R-CNN). By using effective feature extraction combined with a classifier, the clutter and the interference can be automatically detected. Due to the end-to-end architecture and the numerous convolutional features, the deep learning-based method can avoid the difficulty and absence of uniform standard inherent in handcrafted feature design and preselection. Field experimental results show that the Faster R-CNN based method can automatically detect the clutter and interference with decent performance and classify them with high accuracy.

Due to its low transmit power and reduced aperture size of a receiving antenna array, compact high-frequency surface wave radar (HFSWR) suffers from low detection probability, low positioning accuracy, and high false alarm rate. In a multitarget tracking scenario, similar kinematic parameters of adjacent targets raise challenges to the track-to-track association procedure. Taking the measurement uncertainty of compact HFSWR into consideration, a track-to-track association method based on maximum likelihood estimation (MLE) for T/R-R composite compact HFSWR is proposed. First, a multitarget tracking algorithm is applied to plot data sequences acquired by both T/R monostatic and T-R bistatic radars to produce two track sets. Then, the measurement errors of range, azimuth, and Doppler velocity are calculated using the obtained radar track and corresponding automatic identification system (AIS) track data, and a Gaussian distribution model is derived through probability distribution fitting. Subsequently, likelihood functions are established using the obtained Gaussian distribution model to calculate the association cost of tracks for T/R monostatic and T-R bistatic radars, and a cost matrix is obtained. Finally, the Jonker–Volgenant–Castanon (JVC) assignment algorithm is applied to the cost matrix to determine associated track-to-track pairs. Track-to-track association experiments using both simulated and field data were conducted, and the association performance of the proposed method is compared with that of Mahalanobis distance-based nearest neighbor (NN) method. Experimental results demonstrate that the proposed method can effectively resolve association ambiguity and achieve correct track-to-track association in track crossing and adjacent multitarget scenarios.

For onshore high-frequency surface-wave radar (HFSWR), target parameter estimation focuses mainly on distance and velocity demodulation, then on azimuth determination. However, these parameters are difficult to solve accurately for shipborne HFSWR targets due to additional modulation on the echo signal introduced by the forward and six-degree-of-freedom (6-DOF) movement of the platform, causing target points spread and shift in radar Doppler spectra. To overcome this difficulty, the influence of platform motion on target detection is mathematically analyzed in terms of echo signal processing, and then theoretical equations are derived to correct the bias in measurements of the target's state and features. Furthermore, to meet the requirement of shipborne HFSWR installed in limited space, the direction of arrival (DOA) estimation of irregular radar arrays with unequal intervals and arbitrary numbers of antennas is also analyzed. With the derived formulas, the parameters of the shipborne HFSWR target, including the range, radial velocity, and azimuth, can be accurately estimated with the help of inertial navigation system (INS) data. Moreover, both the simulation and the field experiment results validate the theoretical analysis and the derived equations.

Due to its limited transmit power and smaller receiving antenna array, compact high-frequency surface wave radar often encounters increased challenges in detecting and tracking sea-surface targets continuously. In tracking scenarios with dense clutter or multiple targets, weak target signals are often missed due to improper detection thresholds, leading to track fragmentations during target tracking. In order to improve target detection probability and enhance target tracking continuity, a joint detection and tracking (JDT) paradigm, which establishes a closed loop between the detector and tracker, is proposed. When a target of interest is tracked, the tracker sends its predicted range, Doppler velocity, and azimuth back to the detector, then the detector builds a detection gate centered at the predicted range and Doppler velocity on the range–Doppler map. Within the detection gate, an optimal detection threshold dependent on the detection background and tracking environment is determined using reinforcement learning. In this way, a potential target plot may be detected with a higher detection probability and the detected plot is provided for track update. The proposed paradigm employs tracking information to provide adaptive detection parameters for specific targets through reinforcement learning to enhance both target detection and tracking performance. Experimental results with field data demonstrate that compared with traditional detection before tracking scheme, the proposed JDT paradigm achieves a superior performance with the average tracking time on target being increased by 13.33 min and the average missed detection rate being reduced by 0.8 $\%$ .

To address plot-to-track association ambiguities caused by low spatial resolution and measurement uncertainties of compact high-frequency surface wave radar (HFSWR) operating in complex maritime environments, a hybrid framework integrating a target state prediction method based on Transformer model and a plot-to-track association method using graph-based feature representation is proposed. In the target state prediction stage, the Transformer model employs self-attention mechanisms to capture long-term temporal dependencies in historical track data to improve the prediction accuracy of the plot-to-track association gate center. In the plot-to-track association stage, a graph autoencoder (GAE) is used to extract graph structure features of candidate measured plots from their corresponding range-Doppler (R-D) spectra. The GAE encodes the diffusion patterns and spatial correlations of radar echoes on the R-D spectrum into discriminative graph feature vectors. The graph feature vectors, which can enhance both inter-target discrimination and target-clutter differentiation, serve as the basis for association similarity computation. Experimental results demonstrate that the proposed framework significantly reduces target state prediction errors and suppresses false plot-to-track associations, achieving an average tracking time on target of 135.6 minutes, which is improved by 36% compared with the baseline method (motion model-based target state prediction combined with nearest neighbor data association using kinematic parameters).