For the local minimum problem of genetic algorithm in unmanned aerial vehicle route planning, the Metropolis acceptance criteria of simulated annealing algorithm is incorporated into the genetic algorithm in this paper. In the algorithm, the original DEM (Digital Elevation Map) is processed into the smallest threat surface. In order to obtain a more smooth surface of flight, the original digital elevation map are processed in four directions, and then the genetic simulated annealing algorithm is used for three-dimensional route planning in this minimal threat surface. In addition, the distance between the track segment and threats are converted into elevation values and the value is added to the fitness function, a smaller code space was proposed at the same time. The simulation results show that the Genetic Simulated Annealing Algorithm proposed is good.

Ship target recognition is essential for maritime transportation, commercial trade, maritime security, and monitoring illegal activity. The majority of previous ship target recognition models are based on fully-supervised learning, which necessitates vast amounts of labeled training data. However, optical lenses capturing ship images in natural scenarios have numerous complex environments, making feature extraction difficult due to hardware, weather, light, waves, and other factors. Moreover, image annotation is also both expensive and time-consuming. How to effectively learn from unbalanced, limited, and sparsely annotated sample data is a significant challenge. In this paper, we propose a new vision transformer with enhanced self-attention(SAVT) that can locate ship targets in complex environments with just a few shots. SAVT consists of a novel enhanced self-attention(ESA) module and a novel measurement self-adjusting computation(MAC) module to differentiate unique ship classes in complex environments with few labeled samples. The ESA module focuses on the features of the target-region at each layer of the backbone network in order to ensure that the contour detailed features are extracted effectively from ship images with complex environments. The model is then enhanced in terms of speed and stability by utilizing the MAC module. CIB-ships and public MAR-ships datasets are used to evaluate the proposed method. In this paper, the results demonstrate that SAVT achieves good performance on few-shot labeled data under both 1-shot and 5-shot settings, while also providing valuable guidance for maritime ship target recognition with limited labeled samples.

The size and position of a moving ship can vary greatly, resulting in different target sizes within the image captured by an imaging device. This variability can significantly impact the accuracy of ship target recognition. Existing methods for recognizing ship targets are generally designed for clear weather conditions with large target sizes and cannot extract detailed features from images with complex environmental information. To address these issues, we propose a multiscale and multilevel enhanced features (MMEF) representation method to enhance the accuracy of ship target recognition in complex environments. The proposed method utilizes an autocorrelation feature enhancement module, which facilitates the exchange of multilevel semantic feature information to enhance the ability to map specific features in target regions. In addition, a multiscale (MS) module is employed to slice the original image from a global to a local level, thus expanding the range of contour feature representation in the target area, which is especially beneficial for small and complex ship targets. Finally, a gating method combines the detailed features of the target region output from each scale branch for the final recognition of complex environmental ship targets. We evaluated the proposed method on the CIB-ships and the Game-of-ships datasets, which contain images of ships captured in complex environments, and the MAR-ships dataset, which features images of ships in single-background conditions. The experimental results show that our method has improved by 1.04% and 1.05% compared with the suboptimal method on the CIB-ships and the Game-of-ships datasets, respectively, and achieved a good recognition effect on the MAR-ships dataset. Compared with the ship target recognition method based on the transformer structure, the results show that the MMEF method can achieve a good recognition effect at a faster speed.

Harsh sea conditions, uneven illumination, and the variable spatial positions of ships result in ship images captured by imaging systems that contain not only the ship targets but also complex environmental information. This environmental complexity, intertwined with the ship targets, significantly undermines the accuracy of ship target recognition. However, existing methods for recognizing ships are mainly designed to identify large targets in clear weather with uniform illumination. They rarely account for the aforementioned complex environmental information, leading to the loss of critical detailed features in the ship’s target area, particularly in adverse weather and uneven illumination scenarios. To address these challenges, we propose a novel method for recognizing ship targets in complex environments: the Feature Representation Enhancement and Graph Convolutional Combiner Network (FREGNet). We introduce a Feature Representation Enhancement (FRE) module to the backbone of the feature extraction network to enhance the capture of detailed features in the ship’s target area, particularly under illumination noise and cloud-covered conditions. Furthermore, we design a GCN Combiner module based on a Graph Convolutional Network to dynamically combine global feature key points and local detailed feature key points output by the FRE, thereby increasing the quantity of detailed feature information in the ship’s target area. This approach facilitates the accurate classification of ship categories. Experiments were conducted using the CIB-ships, MAR-ships, and Game-of-ships datasets. Compared to suboptimal transformer-based ship target recognition methods, FREGNet improves ship target recognition accuracy by 2.8%, 0.99%, and 1.38%, respectively. The FREGNet method achieves high recognition accuracy at a faster rate.