In order to complete automatic route planning in the complex navigation environment, this paper proposes a quadratic optimization genetic algorithm combining the motion characteristics of the ships. Furthermore, the constraints of the maneuvering characteristics of ship are considered to calculate the accurate planning routes fast. First of all, the turning and speed reduction model of ships are established, which is the foundation for the accurate calculation of approach states between the own ship and target ships. Second, in order to check the position relationship between the planned route and the land objects (such as the islands and rocks) on the chart, a detection algorithm between lines and irregular polygon boundary based on quadtree method is acquired. Third, a new genetic algorithm based on double-cycling optimization is proposed by this paper. Aiming at the complex problem of comprehensive collision avoidance planning under the conditions of static and dynamic obstacles, this paper realizes an efficient and feasible solution of dynamic programming for ship route. Finally, the algorithm is verified on a test fireboat, and the experiment data prove the feasibility and effectiveness of the proposed algorithm by this paper.

Point cloud-based detection focuses on land traffic, rarely marine, facing issues with ships: it struggles in bad weather due to reliance on adverse weather data and fails to detect ships effectively due to overlooking size and appearance differences. Addressing the above challenges, our work introduces point cloud data of marine scenarios under realistically simulated adverse weather conditions and a dedicated Ship Detector tailored for marine environments. To adapt to various maritime weather conditions, we simulate realistic rain and fog in collected marine scene point cloud data. Additionally, addressing the issue of losing geometric and height information during feature extraction for large objects, we propose a Ship Detector. It employs a dual-branch sparse convolution layer for extracting multi-scale 3D feature maps, effectively minimizing height information loss. Additionally, a multi-scale 2D convolution module is utilized, which encodes and decodes feature maps and directly employs 3D feature maps for target prediction. To reduce dependency on existing data and enhance model robustness, our training dataset includes simulated point cloud data representing adverse weather conditions. In maritime point cloud ship detection, our Ship Detector, compared to adjusted small object detectors, demonstrates the best performance.

For the first time, this article introduces a LiDAR Point Clouds Dataset of Ships composed of both collected and simulated data to address the scarcity of LiDAR data in maritime applications. The collected data are acquired using specialized maritime LiDAR sensors in both inland waterways and wide-open ocean environments. The simulated data is generated by placing a ship in the LiDAR coordinate system and scanning it with a redeveloped Blensor that emulates the operation of a LiDAR sensor equipped with various laser beams. Furthermore, we also render point clouds for foggy and rainy weather conditions. To describe a realistic shipping environment, a dynamic tail wave is modeled by iterating the wave elevation of each point in a time series. Finally, networks serving small objects are migrated to ship applications by feeding our dataset. The positive effect of simulated data is described in object detection experiments, and the negative impact of tail waves as noise is verified in single-object tracking experiments. The Dataset is available at https://github.com/zqy411470859/ship_dataset.