In the water transportation, ship speed estimation has become a key subject of intelligent shipping research. Traditionally, Automatic Identification System (AIS) is used to extract the ship speed information. However, transportation environment is gradually becoming complex, especially in the busy water, leading to the loss of some AIS data and resulting in a variety of maritime accidents. To make up for this deficiency, this paper proposes a vessel speed extraction framework, based on Unmanned Aerial Vehicle (UAV) airborne video. Firstly, YOLO v4 is employed to detect the ship targets in UAV image precisely. Secondly, a simple online and real time tracking method with a Deep association metric (Deep SORT) is applied to track ship targets with high quality. Finally, the ship motion pixel is computed based on the bounding box information of the ship trajectories, at the same time, the ship speed is estimated according to the mapping relationship between image space and the real space. Exhaustive experiments are conducted on the various scenarios. Results verify that the proposed framework has an excellent performance with average speed measurement accuracy is above 93% in complex waters. This paper also paves a way to further predict ship traffic flow in water transportation.

Ship speed extraction (SSE) in busy water based on an automatic identification system (AIS) has received widespread attention due to its high efficiency. However, this method is usually degraded by data delay and loss. In this paper, we propose a novel SSE method based on machine vision and unmanned aerial vehicle (UAV) video to measure ship speed and repair AIS data in busy water. Our framework integrates YOLO v4 into simple online and real-time tracking with a deep association metric (Deep SORT) to detect and track ship targets. Specifically, we design a tracking buffer to promote the insensitivity of the tracker under uncertain environmental changes and filter the tracker for measuring speed. Furthermore, a motion vector computation term is proposed based on sparse optical flow and a box diagram. After using camera calibration to convert the motion vector to displacement in the real world, the SSE results are obtained. Exhaustive experiments are conducted on various scenarios, i.e., illumination and ship distribution, from our ship’s remote dataset. The results verify that the proposed framework performs excellently, with an average speed measurement accuracy above 95% in complex waters, and the AIS data repair effect is remarkable. Moreover, it is also proven that machine vision technology can assist AIS information in supervising complex waters and ensuring navigation safety, which paves the way for extracting ship traffic flow information.

Aiming to avoid personal injury caused by the failure of timely medical assistance following a fall by seafarer members working on ships, research on the detection of seafarer’s falls and timely warnings to safety officers can reduce the loss and severe consequences of falls to seafarers. To improve the detection accuracy and real-time performance of the seafarer fall detection algorithm, a seafarer fall detection algorithm based on BlazePose–LSTM is proposed. This algorithm can automatically extract the human body key point information from the video image obtained by the vision sensor, analyze its internal data correlation characteristics, and realize the process from RGB camera image processing to seafarer fall detection. This fall detection algorithm extracts the human body key point information through the optimized BlazePose human body key point information extraction network. In this section, a new method for human bounding-box acquisition is proposed. In this study, a head detector based on the Vitruvian theory was used to replace the pre-trained SSD body detector in the BlazePose preheating module. Simultaneously, an offset vector is proposed to update the bounding box obtained. This method can reduce the frequency of repeated use of the head detection module. The algorithm then uses the long short-term memory neural network to detect seafarer falls. After extracting fall and related behavior data from the URFall public data set and FDD public data set to enrich the self-made data set, the experimental results show that the algorithm can achieve 100% accuracy and 98.5% specificity for the seafarer’s falling behavior, indicating that the algorithm has reasonable practicability and strong generalization ability. The detection frame rate can reach 29 fps on a CPU, which can meet the effect of real-time detection. The proposed method can be deployed on common vision sensors.

Global navigation satellite systems and inertial navigation systems (GNSSs/INSs) based on the cubature Kalman filter (CKF) can provide an effective land vehicle navigation and positioning solution. The accuracy of CKF depends mainly on the prior probability density function (PDF), which is inaccurate when the GNSS signal is temporarily blocked in an urban environment. Although the improved CKF (ICKF) can reduce cubature point errors by using the historical information obtained iteratively, the generation of cubature points is still related to measurement noise. To obtain a more accurate PDF, adjustment off the sensor measurement noise is necessary. In this paper, an adaptive ICKF for GNSS/INS system based on the Mahalanobis distance called MD-ICKF is proposed, which expands the usability of the micro-electronic mechanical system based integrated navigation system in an urban environment. Two lower triangular matrices obtained by Cholesky decomposition are used to adjust the cubature point errors during each iteration. Furthermore, the measurement noise will be inflated to obtain a more accurate PDF when it exceeds the threshold calculated by the MD and chi-square test. The field experiment results show that the proposed method has better positioning accuracy and performance than CKF and ICKF in an occluded environment