Search

In this study, we propose a practical and efficient scheme for ship detection in remote sensing imagery. Our method is developed using both ship body detection and ship wake detection and combines deep learning and feature-based image processing. A deep convolutional neural network is used to achieve ship body detection, and a feature-based processing method is proposed to detect ship wakes. For better analysis, we model the sea region and evaluate the quality of the image. Generally, the wake detection result is used to assist ship detection and obtain the sailing direction. Conventional methods cannot detect ships that are covered by clouds or outside the image boundary. The method proposed in this paper uses the wake to detect such ships, with a certain level of confidence and low false alarm probability in detection. Practical aspects such as the method’s applicability and time efficiency are considered in our method for real applications. We demonstrate the effectiveness of our method in a real remote sensing dataset. The results show that over 93.5% of ships and over 70% of targets with no visible ship body can be successfully detected. This illustrates that the proposed detection framework can fill the gap regarding the detection of sailing ships in a remote sensing image.

Ship detection in remote sensing images plays an important role in maritime surveillance. Recently, convolution neural network (CNN)-based methods have achieved state-of-the-art performance in ship detection. Even so, there are still two problems that remain in remote sensing. One is that the different modal images observed by multiple satellite sensors and the existing dataset cannot satisfy network-training requirements. The other is the false alarms in detection, as the ship target is usually faint in real view remote sensing images and many false-alarm targets can be detected in ocean backgrounds. To solve these issues, we propose a double augmentation framework for ship detection in cross-modal remote sensing imagery. Our method can be divided into two main steps: the front augmentation in the training process and the back augmentation verification in the detection process; the front augmentation uses a modal recognition network to reduce the modal difference in training and in using the detection network. The back augmentation verification uses batch augmentation and results clustering to reduce the rate of false-alarm detections and improve detection accuracy. Real-satellite-sensing experiments have been conducted to demonstrate the effectiveness of our method, which shows promising performance in quantitative evaluation metrics.

In the field of remote sensing technology, the semantic segmentation of remote sensing images carries substantial importance. The creation of high-quality models for this task calls for an extensive collection of image data. However, the manual annotation of these images can be both time-consuming and labor-intensive. This has catalyzed the advent of semi-supervised semantic segmentation methodologies. Yet, the complexities inherent within the foreground categories of these remote sensing images present challenges in preserving prediction consistency. Moreover, remote sensing images possess more complex features, and different categories are confused within the feature space, making optimization based on the feature space challenging. To enhance model consistency and to optimize feature-based class categorization, this paper introduces a novel semi-supervised semantic segmentation framework based on Mean Teacher (MT). Unlike the conventional Mean Teacher that only introduces perturbations at the image level, we incorporate perturbations at the feature level. Simultaneously, to maintain consistency after feature perturbation, we employ contrastive learning for feature-level learning. In response to the complex feature space of remote sensing images, we utilize entropy threshold to assist contrastive learning, selecting feature key-values more precisely, thereby enhancing the accuracy of segmentation. Extensive experimental results on the ISPRS Potsdam dataset and the challenging iSAID dataset substantiate the superior performance of our proposed methodology.

A vessel automatic identification system (AIS) provides a large amount of dynamic vessel information over a large coverage area and data volume. The AIS data are a typical type of big geo-data with high dimensionality, large noise, heterogeneous densities, and complex distributions. This poses a challenge for the clustering and analysis of vessel sailing routes. This study proposes an efficient vessel sailing route clustering and analysis method based on AIS data that uses traffic density images to transform the clustering problem of complex AIS trajectories into an image processing problem. First, a traffic density image is constructed based on the statistics of the preprocessed AIS data. Next, the main sea route regions of traffic density images are extracted based on local image features, geometric structures, and spatial features. Finally, the sailing trajectories are clustered using the extracted sailing patterns. Based on actual vessel AIS data, multimethod comparisons and performance analysis experiments are conducted to verify the feasibility and effectiveness of the proposed method. These experimental results reveal that the proposed method displays potential for the clustering task of challenging vessel sailing routes.

Numerical methods, such as finite element or finite difference, have been widely used in the past decades for modeling solid mechanics problems by solving partial differential equations (PDEs). Differently from the traditional computational paradigm employed in numerical methods, physics-informed deep learning approximates the physics domains using a neural network and embeds physics laws to regularize the network. In this work, a physics-informed neural network (PINN) is extended for application to linear elasticity problems that arise in modeling non-uniform deformation for a typical open-holed plate specimen. The main focus will be on investigating the performance of a conventional PINN approach to modeling non-uniform deformation with high stress concentration in relation to solid mechanics involving forward and inverse problems. Compared to the conventional finite element method, our results show the promise of using PINN in modeling the non-uniform deformation of materials with the occurrence of both forward and inverse problems.

Space-time interpolation is widely used to estimate missing or unobserved values in a dataset integrating both spatial and temporal records. Although space-time interpolation plays a key role in space-time modeling, existing methods were mainly developed for space-time processes that exhibit stationarity in space and time. It is still challenging to model heterogeneity of space-time data in the interpolation model. To overcome this limitation, in this study, a novel space-time interpolation method considering both spatial and temporal heterogeneity is developed for estimating missing data in space-time datasets. The interpolation operation is first implemented in spatial and temporal dimensions. Heterogeneous covariance functions are constructed to obtain the best linear unbiased estimates in spatial and temporal dimensions. Spatial and temporal correlations are then considered to combine the interpolation results in spatial and temporal dimensions to estimate the missing data. The proposed method is tested on annual average temperature and precipitation data in China (1984–2009). Experimental results show that, for these datasets, the proposed method outperforms three state-of-the-art methods—e.g., spatio-temporal kriging, spatio-temporal inverse distance weighting, and point estimation model of biased hospitals-based area disease estimation methods.

An anthomyiid new genus Lopesohylemya with its type species L. qinghaiensis sp. n. from Qinghai, China, is described and figured. It is closely related to Eustalomyia histrio group, which is transferred to present new genus from Eustalomyia, it is suggested by the authors.

Underwater acoustic target recognition (UATR) is crucial for defense and ocean environment monitoring. Although traditional methods and deep learning approaches based on time–frequency domain features have achieved high recognition rates in certain tasks, they rely on manually designed feature extraction processes, leading to information loss and limited adaptability to environmental changes. To overcome these limitations, we proposed a novel end-to-end underwater acoustic target recognition model, 1DCTN. This model directly used raw time-domain signals as input, leveraging one-dimensional convolutional neural networks (1D CNNs) to extract local features and combining them with Transformers to capture global dependencies. Our model simplified the recognition process by eliminating the need for complex feature engineering and effectively addressed the limitations of LSTM in handling long-term dependencies. Experimental results on the publicly available ShipsEar dataset demonstrated that 1DCTN achieves a remarkable accuracy of 96.84%, setting a new benchmark for end-to-end models on this dataset. Additionally, 1DCTN stood out among lightweight models, achieving the highest recognition rate, making it a promising direction for future research in underwater acoustic recognition.

Abstract For the channel estimation problem under α-stable distributed impulse interference, the traditional fixed-step adaptive filtering cannot satisfy the fast convergence speed and low steady-state error at the same time, whereas the variable-step method is able to effectively solve this contradiction. This paper proposes an improved variable step-size least mean p-power adaptive algorithm that offers good robustness against impulsive noise. The proposed algorithm takes into account the linkage between the errors and uses the adjustment of the step size based on the errors of the current moment and the previous k moments, thus overcoming the problems of poor anti-noise performance and large steady-state fluctuations of the fixed-step size algorithm. This algorithm ensures that the step size does not change abruptly when the system is disturbed by impulse noise and can achieve a lower steady-state error. The simulation results show that the algorithm has better convergence than the traditional fixed step-size algorithm and the existing variable step-size algorithm under the interference of impulsive noise.

The orthogonal time frequency space (OTFS) modulation technique can provide reliable communication in time-varying channels. Due to the dispersive characteristics of underwater acoustic channels, this paper proposes an OTFS-IM underwater acoustic communication system based on Hamming distance optimization to reduce the impact of dispersion in underwater acoustic communication. Firstly, the OTFS-IM underwater acoustic communication system is introduced, which introduces index modulation into the Delay–Doppler (DD) domain to make the OTFS system have stronger anti-Delay–Doppler capability. In contrast, since there is index sequence redundancy in a specific index combination, a Hamming distance optimization model is used to eliminate the redundant combination in the specific index combination sequence and further improve the bit error rate performance of the system. In addition, the Hamming distance optimized OTFS-IM underwater acoustic communication system is verified by simulation analysis. The results show that the proposed Hamming distance optimized OTFS-IM can achieve more reliable bit error rate performance.