Due to the high error frequency of the existing methods in identifying a ship’s navigational intention, accidents frequently occur at intersections. Therefore, it is urgent to improve the ability to perceive ship intention at intersections. In this paper, we propose an algorithm based on the fusion of image sequence and radar information to identify the navigation intention of ships at intersections. Some existing algorithms generally use the Automatic Identification System (AIS) to identify ship intentions but ignore the problems of AIS delay and data loss, resulting in unsatisfactory effectiveness and accuracy of intention recognition. Firstly, to obtain the relationship between radar and image, a cooperative target composed of a group of concentric circles and a central positioning radar angle reflector is designed. Secondly, the corresponding relationship of radar and image characteristic matrix is obtained after employing the RANSAC method to fit radar and image detection information; then, the homographic matrix is solved to realize radar and image data matching. Thirdly, the YOLOv5 detector is used to track the ship motion in the image sequence. The visual measurement model based on continuous object tracking is established to extract the ship motion parameters. Finally, the motion intention of the ship is predicted by integrating the extracted ship motion features with the position information of the shallow layer using a Bayesian framework. Many experiments on real data sets show that our proposed method is superior to the most advanced method for ship intention identification at intersections.

Semantic segmentation as one of the most popular scene perception techniques has been studied for autonomous vehicles. However, deep learning-based solutions rely on the volume and quality of data and knowledge from specific scene might not be incorporated. A novel knowledge-driven semantic segmentation method is proposed for waterway scene perception. Based on the knowledge that water is irregular and dynamically changing, a Life Time of Feature (LToF) detector is designed to distinguish water region from surrounding scene. Using a Bayesian framework, the detector as the likelihood function is combined with U-Net based semantic segmentation to achieve an optimized solution. Finally, two public datasets and typical semantic segmentation networks, FlowNet, DeepLab and DVSNet are selected to evaluate the proposed method. Also, the sensitivity of these methods and ours to dataset is discussed.

The demand for non-powered facility towing is increasing with the development of large-scale offshore projects. It is of great interest for its safe operation to measure the state of the towing process in real time. This paper proposed a computer vision algorithm designed to measure the tug yawing during the towing operation by estimating the towing line angle. The geometrical projection of the towing line from 3D to 2D is described in detail. By fixing the camera at specific locations and simplifying the calculation procedure, the towing line angle in the 3D world can be estimated by the line angle in the image. Firstly, the sea–sky line is detected to estimate the rolling angle of the tug in the captured image. Then, the towing line angle is calculated by an image processing method. At the same time, the estimation of the towing angle is achieved through the captured video data analysis. Finally, field experiments were carried out and the results demonstrated that this method is suitable for real-time calculation of the towing angle during the towing operation.

In the field of automatic detection of ship exhaust behavior, a deep learning-based multi-sensor hierarchical detection method for tracking inland river ship chimneys is proposed to locate the ship exhaust behavior detection area quickly and accurately. Firstly, the primary detection uses a target detector based on a convolutional neural network to extract the shipping area in the visible image, and the secondary detection applies the Ostu binarization algorithm and image morphology operation, based on the infrared image and the primary detection results to obtain the chimney target by combining the location and area features; further, the improved DeepSORT algorithm is applied to achieve the ship chimney tracking. The results show that the multi-sensor-based hierarchical detection and tracking method can achieve real-time detection and tracking of ship chimneys, and can provide technical reference for the automatic detection of ship exhaust behavior.