Object detection in underwater environments presents significant challenges due to the inherent limitations of sonar imaging, such as noise, low resolution, lack of texture, and color information. This paper introduces AquaYOLO, an enhanced YOLOv8 version specifically designed to improve object detection accuracy in underwater sonar images. AquaYOLO replaces traditional convolutional layers with a residual block in the backbone network to enhance feature extraction. In addition, we introduce Dynamic Selection Aggregation Module (DSAM) and Context-Aware Feature Selection (CAFS) in the neck network. These modifications allow AquaYOLO to capture intricate details better and reduce feature redundancy, leading to improved performance in underwater object detection tasks. The model is evaluated on two standard underwater sonar datasets, UATD and Marine Debris, demonstrating superior accuracy and robustness compared to baseline models.

Underwater sonar target recognition is crucial in fields such as national defense, navigation, and environmental monitoring. However, it faces issues such as the complex characteristics of ship-radiated noise, imbalanced data distribution, non-stationarity, and bottlenecks of existing technologies. This paper proposes the MultiFuseNet-AID network, aiming to address these challenges. The network includes the TriFusion block module, the novel lightweight attention residual network (NLARN), the long- and short-term attention (LSTA) module, and the Mamba module. Through the TriFusion block module, the original, differential, and cumulative signals are processed in parallel, and features such as MFCC, CQT, and Fbank are fused to achieve deep multi-domain feature fusion, thereby enhancing the signal representation ability. The NLARN was optimized based on the ResNet architecture, with the SE attention mechanism embedded. Combined with the long- and short-term attention (LSTA) and the Mamba module, it could capture long-sequence dependencies with an O(N) complexity, completing the optimization of lightweight long sequence modeling. At the same time, with the help of feature fusion, and layer normalization and residual connections of the Mamba module, the adaptability of the model in complex scenarios with imbalanced data and strong noise was enhanced. On the DeepShip and ShipsEar datasets, the recognition rates of this model reached 98.39% and 99.77%, respectively. The number of parameters and the number of floating point operations were significantly lower than those of classical models, and it showed good stability and generalization ability under different sample label ratios. The research shows that the MultiFuseNet-AID network effectively broke through the bottlenecks of existing technologies. However, there is still room for improvement in terms of adaptability to extreme underwater environments, training efficiency, and adaptability to ultra-small devices. It provides a new direction for the development of underwater sonar target recognition technology.