Robust detection and recognition of water surfaces are critical for autonomous navigation of unmanned surface vehicles (USVs), since any none-water region is likely an obstacle posing a potential danger to the sailing vehicle. A novel water region visual detection method is proposed in this paper. First, the input image pixels are clustered into different regions and each pixel is assigned a label tag and a confidence value by adaptive multistage segmentation algorithm. Then the resulting label map and associated confidence map are fed into a convolutional neural network (CNN) as training samples to train the network online. Finally, the online trained CNN is used to segment the input image again but with greater precision and stronger robustness. Compared with other deep-learning image segmentation algorithms, the proposed method has two advantages. Firstly, it dispenses with the need of manual labeling training samples which is a costly and painful task. Secondly, it allows real-time online training for CNN, making the network adaptive to the navigational environment. Another contribution of this work relates to the training process of neuro network. An effective network training method is designed to learn from the imperfect training data. We present the experiments in the lake with a various scene and demonstrate that our proposed method could be applied to recognize the water region in the unknown navigation environment automatically.

For the navigation of an unmanned surface vehicle (USV), detection and recognition of the water-shore-line (WSL) is an important part of its intellectualization. Current research on this issue mainly focuses on the straight WSL obtained by straight line fitting. However, the WSL in the image acquired by boat-borne vision is not always in a straight line, especially in an inland river waterway. In this paper, a novel three-step approach for WSL detection is therefore proposed to solve this problem through the information of an image sequence. Firstly, the initial line segment pool is built by the line segment detector (LSD) algorithm. Then, the coarse-to-fine strategy is used to obtain the onshore line segment pool, including the rough selection of water area instability and the fine selection of the epipolar constraint between image frames, both of which are demonstrated in detail in the text. Finally, the complete shore area is generated by an onshore line segment pool of multi-frame images, and the lower boundary of the area is the desired WSL. In order to verify the accuracy and robustness of the proposed method, field experiments were carried out in the inland river scene. Compared with other detection algorithms based on image processing, the results demonstrate that this method is more adaptable, and can detect not only the straight WSL, but also the curved WSL.

In order to monitor and manage vessels in channels effectively, identification and tracking are very necessary. This work developed a maritime unmanned aerial vehicle (Mar-UAV) system equipped with a high-resolution camera and an Automatic Identification System (AIS). A multi-feature and multi-level matching algorithm using the spatiotemporal characteristics of aerial images and AIS information was proposed to detect and identify field vessels. Specifically, multi-feature information, including position, scale, heading, speed, etc., are used to match between real-time image and AIS message. Additionally, the matching algorithm is divided into two levels, point matching and trajectory matching, for the accurate identification of surface vessels. Through such a matching algorithm, the Mar-UAV system is able to automatically identify the vessel’s vision, which improves the autonomy of the UAV in maritime tasks. The multi-feature and multi-level matching algorithm has been employed for the developed Mar-UAV system, and some field experiments have been implemented in the Yangzi River. The results indicated that the proposed matching algorithm and the Mar-UAV system are very significant for achieving autonomous maritime supervision.

The intelligentization of unmanned surface vehicles (USVs) has recently attracted intensive interest. Visual perception of the water scenes is critical for the autonomous navigation of USVs. In this paper, an adaptive semantic segmentation method is proposed to recognize the water scenes. A semantic segmentation network model is designed to classify each pixel of an image into water, land or sky. The segmentation result is refined by the conditional random field (CRF) method. It is further improved accordingly by referring to the superpixel map. A weight map is generated based on the prediction confidence. The network trains itself with the refined pseudo label and the weight map. A set of experiments were designed to evaluate the proposed method. The experimental results show that the proposed method exhibits excellent performance with few-shot learning and is quite adaptable to a new environment, very efficient for limited manual labeled data utilization.

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.

Water-shore-line (WSL) detection in complex inland river background plays an important role for detection of water surface targets and the security of vessels. However, because of the blurred image and water ripple caused by the environmental factors such as rain, snow, fog, wind and sunlight, it is very difficult to detect and recognize the WSL. In order to deal with these problems, the WSL detection method is designed and implemented in the paper. First of all, a gradient detection operator based on distance is proposed to improve the sensitivity of the edge detection to the noise. Secondly, the edge image is processed by the line shape filter operator because of the characteristics of the water ripple. And then the WSL is obtained by straight line fitting using the optimized ransac algorithm. Finally, the results of field experiments show that the method is effective and timeliness in a variety of complex environments.