Ship position prediction is the key to inland river and sea navigation warning. Maritime traffic control centers, according to ship position monitoring, ship position prediction and early warning, can effectively avoid collisions. However, the prediction accuracy and computational efficiency of the ship’s future position are the key problems to be solved. In this paper, a path prediction model (GA–ACO–BP) combining a genetic algorithm, an ant colony algorithm and a BP neural network is proposed. The model is first used to perform deep pretreatment of raw AIS data, with the main body of the BP neural network as a prediction model, focused on the complementarity between genetic and ant colony algorithms, to determine the ant colony initialization pheromone concentration by the genetic algorithm, design the hybrid genetic–ant colony algorithm, and optimize this to the optimal weight and threshold of the BP neural network, in order to improve the convergence speed and effect of the traditional BP neural network. The test results show that the model greatly improves the fitness of track prediction, with higher accuracy and within a shorter time, and has a certain real-time and extensibility for track prediction of different river segments.

Ship position prediction plays a key role in the early warning and safety of inland waters and maritime navigation. Ship pilots must have in-depth knowledge of the future position of their ship and target ship in a specific time period when maneuvering the ship to effectively avoid collisions. However, prediction accuracy and computing efficiency are crucial issues that need to be worked out at present. To solve these problems, in this paper, the deep long short-term memory network framework (LSTM) and genetic algorithm (GA) are introduced to predict the ship trajectory of inland water. Firstly, the collected actual automatic identification system (AIS) data are preprocessed and a series of typical trajectories are extracted from them; then, the LSTM network is used to predict the typical trajectories in real time. Considering that the hyperparameters of the LSTM network have difficulty obtaining the optimal solution manually, the GA is used to optimize hyperparameters of LSTM; finally, the GA-LSTM trajectory prediction model is constructed with the optimal network parameters and compared with the traditional support vector machine (SVM) model and LSTM model. The experimental results show that the GA-LSTM model effectively improves the accuracy and speed of trajectory prediction, with outstanding performance and good generalization, which possess certain reference values for the development of collision avoidance of unmanned ships.

Objective: In this paper, we propose a Sine chaos mapping-based improved sparrow search algorithm (SSA) to optimize the BP neural network for trajectory prediction of inland river vessels because of the problems of poor accuracy and easy trapping in local optimum in BP neural networks. Method: First, a standard BP model is constructed based on the AIS data of ships in the Yangtze River section. A Sine-BP model is built using Sine chaos mapping to assign neural network weights and thresholds. Finally, a Sine-SSA-BP model is built using the sparrow search algorithm (SSA) to solve the optimal solutions of the neural network weights and thresholds. Result: The Sine-SSA-BP model effectively improves the initialized population of uniform distribution, and reduces the problem that population intelligence algorithms tend to be premature. Conclusions: The test results show that the Sine-SSA-BP neural network has higher prediction accuracy and better stability than conventional LSTM and SVM, especially in the prediction of corners, which is in good agreement with the real ship navigation trajectory.

To improve the navigation safety of inland river ships and enrich the methods of environmental perception, this paper studies the recognition and depth estimation of inland river ships based on binocular stereo vision (BSV). In the stage of ship recognition, considering the computational pressure brought by the huge network parameters of the classic YOLOv4 model, the MobileNetV1 network was proposed as the feature extraction module of the YOLOv4 model. The results indicate that the mAP value of the MobileNetV1-YOLOv4 model reaches 89.25%, the weight size of the backbone network was only 47.6 M, which greatly reduced the amount of computation while ensuring the recognition accuracy. In the stage of depth estimation, this paper proposes a feature point detection and matching algorithm based on the ORB algorithm at sub-pixel level, that is, firstly, the FSRCNN algorithm was used to perform super-resolution reconstruction of the original image, to further increase the density of image feature points and detection accuracy, which was more conducive to the calculation of the image parallax value. The ships’ depth estimation results indicate that when the distance to the target is about 300 m, the depth estimation error is less than 3%, which meets the depth estimation needs of inland ships. The ship target recognition and depth estimation technology based on BSV proposed in this paper makes up for the shortcomings of the existing environmental perception methods, improves the navigation safety of ships to a certain extent, and greatly promotes the development of intelligent ships in the future.

Real-time and accurate detection of ships plays a vital role in ensuring navigation safety and ship supervision. Aiming at the problems of large parameters, large computation quantity, poor real-time performance, and high requirements for memory and computing power of the current ship detection model, this paper proposes a ship target detection algorithm MC-YOLOv5s based on YOLOv5s. First, the MobileNetV3-Small lightweight network is used to replace the original feature extraction backbone network of YOLOv5s to improve the detection speed of the algorithm. And then, a more efficient CNeB is designed based on the ConvNeXt-Block module of the ConvNeXt network to replace the original feature fusion module of YOLOv5s, which improves the spatial interaction ability of feature information and further reduces the complexity of the model. The experimental results obtained from the training and verification of the MC-YOLOv5s algorithm show that, compared with the original YOLOv5s algorithm, MC-YOLOv5s reduces the number of parameters by 6.98 MB and increases the mAP by about 3.4%. Even compared with other lightweight detection models, the improved model proposed in this paper still has better detection performance. The MC-YOLOv5s has been verified in the ship visual inspection and has great application potential. The code and models are publicly available at https://github.com/sakura994479727/datas.