Traditional underwater acoustic reconnaissance technologies are limited in directly detecting underwater acoustic communication signals. This paper proposes a dual-feature ResNet–Transformer model with two innovative breakthroughs: (1) A dual-modal fusion architecture of ResNet and Transformer is constructed using residual connections to alleviate gradient degradation in deep networks and combining multi-head self-attention to enhance long-distance dependency modeling. (2) The time–frequency representation obtained from the smooth pseudo-Wigner–Ville distribution is used as the first input branch, and higher-order statistics are introduced as the second input branch to enhance phase feature extraction and cope with channel interference. Experiments on the Danjiangkou measured dataset show that the model improves the accuracy by 6.67% compared with the existing Convolutional Neural Network (CNN)–Transformer model in long-distance ranges, providing an efficient solution for modulation recognition in complex underwater acoustic environments.

Precise orientation information facilitates target recognition of sonar images. Traditional orientation estimation methods, including the Hough transform method, have poor antinoise abilities, so they cannot achieve high estimation precision for sonar images, which usually have low signal-to-noise ratios. The convolutional neural network (CNN) regression method is sensitive to image affine transformations and requires extensive computation, so it cannot achieve strong robustness or high speed. To achieve high-precision, high-speed, and robust orientation estimation of sonar image targets, we present a novel orientation estimation method via the wavelet subimage energy ratio (WSER). The WSER varies with the rotation angles of images and has the highest value when the long axes of targets are vertical. It is translational and scale invariant and does not need supervised training. Therefore, we propose estimating orientations of sonar image targets by finding the max of the WSER to achieve high precision, high speed, and strong robustness to the translation and scale transformations of images. The results of experiments on a self-made sonar image dataset show that the mean absolute error (MAE) of the proposed method is 7.9°, while the MAEs of the CNN regression method and traditional methods are 10.1 and 22.9°, respectively. In addition, the proposed method is six times faster than the CNN regression method. The proposed orientation estimation method has also been applied to align the orientation of sonar images and CNN can achieve state-of-the-art performance for rotated target recognition using the aligned images. Data and codes are publicly available.

Two-dimensional phase unwrapping (2-D PU) is the process of converting the measured phase into the real phase in interferometric signal processing. Reliable unwrapping results are critical for digital elevation model (DEM) generation using interferometric synthetic aperture radar (InSAR) and interferometric synthetic aperture sonar (InSAS). The majority of previous research has concentrated on accuracy. Whereas the computational efficiency must be taken into account for the interferometric measurement system that requires real-time processing. This paper proposes a low-time-consuming algorithm that can accomplish high-precision 2-D PU for this application scenario. The neural network and a new path-based 2-D PU algorithm make up this algorithm. First, the incorrect region in the gradient field is predicted and corrected using the neural network. The output channelwise variance is then calculated and used to generate the quality maps. Finally, to achieve phase reconstruction, the path-based algorithm performs path planning and flooding integral according to quality maps and compensated gradient. This paper also provides a recommended data structure implementation to ensure the algorithm's high efficiency. Experimental results using InSAR and InSAS data show that the proposed algorithm is highly efficient and accurate.

Two-dimensional phase unwrapping is a crucial step in interferometric signal processing. A phase quality map can help the unwrapping algorithm deal with low-quality and fast-changing regions. However, because existing algorithms cannot calculate a quality map representing the gradient quality directly, it is usually necessary to approximate the gradient quality with phase quality to assist the network-based phase unwrapping algorithm. Furthermore, they cannot withstand intense noise in low-quality regions, resulting in many errors in path-based algorithms. To address the aforementioned issues, this paper analyzes the essence of a quality map and proposes a quality map generation method based on a convolutional neural network. The generated quality maps are a pair, each indicating the quality of horizontal and vertical gradients. Experiments show that the quality map generated by this method can help path-based and network-based algorithms perform better.

Two-dimensional phase unwrapping is a crucial step in interferometric signal processing. The accuracy of phase unwrapping will significantly affect subsequent processing. Existing algorithms perform poorly in areas with rapid terrain changes or with low coherence. In order to solve the above problems, this letter proposes a method of using neural network to predict residuals, followed by the minimum L ¹ -norm algorithm for phase reconstruction. The network for predicting residuals is called RPNet, and its training phase employs a continuous relaxation strategy, allowing for the construction of more complex, specialized loss terms. The proposed method overcomes the effects of noise and terrain changes due to the accurate prediction of residuals. The compensated phase gradients enable the minimum L ¹ -norm algorithm to reconstruct phases more accurately. The experimental results performed on simulation and InSAR data demonstrate the effectiveness of the proposed method.

To address the issue of phase mismatch, mainlobe broadening, image defocusing, and high computational complexity caused by spherical wavefront propagation in near-field imaging of uniform linear array (ULA) imaging sonar, this paper proposes an interpolation-free near-field frequency-domain beamforming algorithm for uniform linear arrays. Under the considered operating conditions, the exact range history is approximated as the sum of a range-dependent quadratic term and a range-independent linear term with respect to the element position. The quadratic term produces negligible envelope migration; therefore, only its phase needs to be compensated. By contrast, the linear term produces more significant range migration, which is corrected together with its associated phase through range-domain and azimuth-domain FFT processing. Under the adopted range-history approximation and discrete sampling conditions, this implementation avoids the explicit point-by-point fractional-delay interpolation required by the backprojection (BP) algorithm. The proposed method substantially reduces the computational cost while maintaining near-field focusing performance comparable to that of the BP algorithm. For the simulated data, the runtime is reduced from 58.23 s to 0.41 s, with only a 0.1% broadening of the azimuth impulse-response width and a 0.11 dB degradation in the peak sidelobe ratio. For the measured lake-trial data, the runtime is reduced from 50.18 s to 0.29 s.