Instance segmentation of ships plays a crucial role in tasks such as monitoring, identification, and tracking, thereby supporting intelligent navigation. However, the wide variability in ship shapes and scales, coupled with environmental interference, leads to poor performance of existing methods perform in Ship Contour extraction. To address this issue, this paper proposes a novel Ship Contour method based on curve recursion.

By enhancing CenterNet with hierarchical feature extraction and integrating the Deep Layer Aggregation-60 backbone network, the proposed method achieves a balance between accuracy and speed. The Block structure is optimized, and an ECA channel attention mechanism is incorporated to strengthen feature extraction, while the Mish activation function replaces ReLU to improve adaptability in deep learning. In addition, a translation-invariant contour deformation method and a dynamic matching loss function are introduced to accelerate the final contour extraction.

On the dedicated 2023Ship-seg dataset containing 2300 samples, the proposed method achieved an average precision of AP_0.5∶0.95 = 64.0% and a recall rate of AR_0.5∶0.95 = 67.9%, outperforming all mainstream instance segmentation algorithms.

The method can significantly improve visual processing performance in ship monitoring and intelligent navigation scenarios.

Current ship navigation decision-making systems struggle to demonstrate superior performance in undefined sailing scenarios. Given the broad applicability of large language models （LLMs） in unknown scenarios, this study proposes a dual-LLM-core-driven adaptive ship navigation agent architecture （Nav-DLLC） to address this issue.

Nav-DLLC employs ReAct-based prompting to decompose complex navigation tasks into manageable subtasks and invoke external tools for information collection, reducing LLM errors. Subsequently, a small-parameter LLM fine-tuned with low-rank adaptation （LoRA） serves as the collision avoidance core, processing unstructured data to generate COLREG-compliant decisions.

Simulation experiments show that Nav-DLLC achieves outstanding performance in both traditional ship collision avoidance tasks and unstructured dynamic scenarios. Its collision avoidance accuracy is 86%, and its behavior compliance rate is 90%, significantly outperforming LLM baselines and traditional methods such as the Dynamic Window Approach （DWA） and Artificial Potential Field （APF）. The decision core's single-decision latency is 11.13 seconds, higher than the 0.73 seconds of traditional methods, yet still within the safe time window for collision avoidance decision-making.

Nav-DLLC bridges the gap between traditional navigation systems and LLM technology, providing a safe and efficient intelligent decision-making paradigm for complex navigation environments and promoting the intelligent development of ship navigation.

It is vital to detect and track ships during coastal monitoring and ship navigation over long distances in complex circumstances. However, due to their small size and unclear features, they can be readily confused with shorelines, noise, and rocks, making them sometimes difficult to spot immediately. To address this issue, a novel ship detection method called ShipDet is proposed which significantly improves performance through the design of a dedicated backbone network, improved feature extraction process, and constrained microscopic detection heads.

First, this method constructs a feature fusion and extraction network that is highly sensitive to small objects by integrating the Swin Transformer module (STR) with the classic CSPDarknet53 network. This enhances the correlation between small target features and the environment, establishing associations between ships and waterways, ships and other ships, and ships and coastlines, while suppressing irrelevant information. Subsequently, considering the uneven distribution and minor scale variations of ship targets in the dataset, two detection layers are retained to reduce model parameters and further enhance model performance. Moreover, the method employs the SCYLLA-IoU (SIoU) loss function to constrain the detection heads, thereby reducing regression freedom and improving detection accuracy and robustness.

To validate the proposed method, a dataset called 2023ships is established which consists of up to 9 000 samples covering various scenarios such as inland rivers, coastal areas, daytime, nighttime, and foggy weather. During testing, the proposed method demonstrates superior overall ship detection performance compared to other algorithms, with a mAP of 92.9%, a precision rate of 92.1%, and a parameter size of 35 366 310.

The proposed method can greatly benefit the fields of maritime monitoring and intelligent navigation.