Maritime ship detection plays a crucial role in smart ships and intelligent transportation systems. However, adverse maritime weather conditions, such as rain streak and fog, can significantly impair the performance of visual systems for maritime traffic. These factors constrain the performance of traffic monitoring systems and ship-detection algorithms for autonomous ship navigation, affecting maritime safety. The paper proposes an approach to resolve the problem by visually removing rain streaks and fog from images, achieving an integrated framework for accurate ship detection. Firstly, the paper employs an attention generation network within an adversarial neural network to focus on the distorted regions of the degraded images. The paper also utilizes a contextual encoder to infer contextual information within the distorted regions, enhancing the credibility of image restoration. Secondly, a weighted bidirectional feature pyramid network (BiFPN) is introduced to achieve rapid multi-scale feature fusion, enhancing the accuracy of maritime ship detection. The proposed GYB framework was validated using the SeaShip dataset. The experimental results show that the proposed framework achieves an average accuracy of 96.3%, a recall of 95.35%, and a harmonic mean of 95.85% in detecting maritime traffic ships under rain-streak and foggy-weather conditions. Moreover, the framework outperforms state-of-the-art ship detection methods in such challenging weather scenarios.

Ship fire is one of the greatest dangers to ship navigation safety. Nevertheless, typical detection methods have limited detection effectiveness and accuracy due to distance restrictions and ship motion. Although the issue can be addressed by image recognition algorithms based on deep learning, the computational complexity and efficiency for ship detection are tough. This paper proposes a lightweight target identification technique based on the modified YOLOv4-tiny algorithm for the precise and efficient detection of ship fires, taking into account the distinctive characteristics of ship fires and the marine environment. Initially, a multi-scale detection technique is applied to broaden the detection range and integrate deep semantic information, thereby enhancing the feature information of small targets and obscured objects and improving the detection precision. Then, the proposed algorithm employs the SE attention mechanism for inter-channel feature fusion to improve the capability of feature extraction and the precision of ship fire detection. Last but not least, picture transformation and migration learning are added to the small ship fire dataset to accelerate the convergence pace, improve the convergence effect, and reduce dataset dependence. The simulation experiments reveal that the proposed I-YOLOv4-tiny + SE model outperforms the benchmark algorithm in terms of ship fire detection accuracy and detection efficiency and that it satisfies the real-time ship fire warning criteria in demanding maritime environments.

Ship pollution emissions have attracted increasing attention in the maritime field due to the massive growth of maritime traffic activities. It is important to identify the ship emissions (SEs) magnitude and corresponding spatial and temporal distributions for the purposes of developing appropriate strategies to mitigate environment pollution. The aim of this study was to estimate ship pollution emissions with various typical merchant ship types under different sailing conditions. We estimated the emission variation with a ship traffic emission assessment model (STEAM2), and then the ship pollution emission distribution was further visualized using ArcGIS. We collected data from the automatic identification system (AIS) for ships in New York Harbor and further analyzed the spatiotemporal distribution of pollutant emissions from ships. The experimental results demonstrate that the ship pollutant emission volume in the New York Harbor area in 2022 was 3340 t, while the pollution in terms of CO, SO₂, C_XH_X, PM₁₀, NO_X, and PM_2.5 was 136, 1421, 66, 185, 1384, and 148 t, respectively. The overall SEs from container ships, passenger ships, and tankers account for a large amount of pollution discharge. The pollutant emissions of container ships are significantly greater than that of their counterparts. Moreover, the spatiotemporal distributions of ship pollutant discharge can vary significantly among different ship types and sailing conditions.

Localization is one of the most critical tasks in wireless sensor networks, but achieving a relatively accurate location estimation is challenging when there have Byzantine fault and non-line-of-sight (NLOS) bias simultaneously. In this context, a localization method, based on received signal strength (RSS), is proposed in this letter to mitigate the impact of Byzantine fault and NLOS bias on the localization accuracy of wireless sensor networks. The proposed method relies on a Byzantine fault-tolerant localization algorithm (BFLA), which converts the localization problem into a generalized trust-region subproblem (GTRS) by applying certain approximations. In order to obtain a feasible solution to the GTRS, a blockcoordinate update (BCU) function with a regularization term is used to divide the localization problem into two subproblems. An iterative method, whose start-point is obtained by an unconstrained squared-range (USR) algorithm, is then used to obtain a solution. Numerical simulations are carried out to show the effectiveness of the proposed method, compared with the state-of-the-art approaches in different scenarios.

In this letter, received signal strength (RSS)-based target localization with uncertainty in transmit power (UTP) is studied. First, the localization-based alternating nonnegative constrained least squares (ANCLS) framework is conducted. A two-phase optimization method, i.e., a matrix factorization-based min-max strategy (MFMM), is then presented to figure out the solution. The first phase of optimization is based on a matrix factorization approach, i.e., active set method (ASM). However, ASM may drop to a local minimum. Therefore, a min-max strategy based on a Taylor linearization approximation is involved in the second phase, where the objective is split into a convex quadratic and a concave term. The target position and UTP are refined simultaneously in the iteration via solving a sequence of convex problems, in which the solution obtained by ASM is to be the initiation. Additionally, to evaluate the effectiveness of MFMM, both the computational complexity and the Cramer-Rao lower bound (CRLB) are analyzed. Simulations are carried out to illustrate the outperformance, compared with other state-of-the-art methods in different scenarios.