This paper proposed an integrated waveform design and parameter optimization method to realize real-time detection and communication for inverted echo sounders (IES). The approach balances detection performance and communication quality in active sonar systems. An integrated detection– communication waveform (GIDC) is developed using the orthogonality and parameter diversity of generalized sinusoidal frequency modulation (GSFM). The waveform incorporates differential binary phase-shift keying (DBPSK) modulation and superimposed orthogonal GSFM signals, enabling simultaneous acoustic detection and data transmission. To enhance performance, parameter optimization constraints are formulated for the carrier GSFM based on quantitative ambiguity function (AF) analysis and bit error rate (BER) metrics, and are solved using an improved genetic algorithm (GA). The optimization effectively suppresses autocorrelation sidelobes, improves reverberation suppression, and ensures reliable error rate performance. The simulation results on Gaussian and vertical underwater acoustic channels confirm that the proposed waveform achieves robust joint detection and communication. Compared with conventional waveforms, the GIDC exhibits higher detection-delay accuracy and lower BER, demonstrating excellent integrated performance suitable for underwater applications.

Subsea pipelines are prone to exposure due to natural factors such as earthquakes and vortices, which necessitates regular condition monitoring. Multi-beam echo sounders (MBES) can provide high-precision seabed topographic information, while side-scan sonar (SSS) excels at capturing high-resolution seabed texture features. The integration of these two data sources can complement each other, thereby improving the detection accuracy of subsea pipelines. To achieve effective fusion, high-precision spatial registration is required. However, existing registration algorithms still face challenges such as uneven feature point distribution, dependence on prior knowledge, and unstable matching. This paper proposes a multi-source sonar image registration algorithm for subsea pipelines, named A Hierarchical Feature Structure-Driven Method for Multi-Source Sonar Image Registration of Subsea Pipelines (HFSM). First, the method designs a grid-based multi-scale corner detection (MS-CD), which effectively enhances the spatial distribution balance of feature points. Next, a multi-window geometric-texture joint feature descriptor (MW-GTD) is proposed, which combines direction-sensitive curvature and spatial shadow distribution features within different scale windows. Finally, a multi-layer coarse-to-fine guided matching strategy (ML-CFGM) is introduced to enhance the matching stability of images in feature-sparse regions and realize multi-layer feature matching. The superiority of the proposed method is validated with real-world data, providing technical support for the efficient registration of MBES and SSS images and subsea pipeline detection.

Automatic modulation recognition (AMR) of underwater acoustic (UWA) signals is incredibly challenging due to the complexity of UWA channels and the severity of ocean noise. In the presence of noise interference, single-modal features fail to fully represent the characteristics of different modulated signals. While the in-phase/quadrature (I/Q) and time-frequency maps can adequately represent the signal features in the time, frequency, and time-frequency domains, the direct integration of the two modalities is ineffective because of the variations in shape, information granularity, and noise manifestation. To address the low recognition rate caused by the above issues, we propose a two-stream transformer (TSTR) based network for AMR of UWA signals. First, the input pre-processing layer obtains the I/Q and time-frequency features from the received signals. Then, the feature capture layer extracts high-dimensional signal features in the time, frequency, and time-frequency domains. Finally, the classification layer estimates the modulation of the signals. A multi-head self-attention module with adaptive soft thresholding is used in the feature capture layer to provide noise reduction and redundant feature rejection while retaining context information. Moreover, multi-scale ghost convolution is employed to address the inability of the transformer to efficiently extract spatial characteristics from the signals. Results are presented using real UWA channels from the Watermark dataset for two different seas which show that the TSTR improves recognition by 1.2% and 5.9% over the best existing model. Further, it has better generalization capabilities and the model has a small number of parameters so the time complexity is low.