Search

Accurate ship trajectory prediction is crucial for real-time vessel position tracking and maritime safety management. However, existing methods for ship trajectory prediction encounter significant challenges. They struggle to effectively extract long-term and complex spatial–temporal features hidden within the data. Moreover, they often overlook correlations among multivariate dynamic features such as longitude (LON), latitude (LAT), speed over ground (SOG), and course over ground (COG), which are essential for precise trajectory forecasting. To address these pressing issues and fulfill the need for more accurate and comprehensive ship trajectory prediction, we propose a novel and integrated approach. Firstly, a Trajectory Point Correlation Attention (TPCA) mechanism is devised to establish spatial connections between trajectory points, thereby uncovering the local trends of trajectory point changes. Subsequently, a Temporal Pattern Attention (TPA) mechanism is introduced to handle the associations between multiple variables across different time steps and capture the dynamic feature correlations among trajectory attributes. Finally, a Great Circle Route Loss Function (GCRLoss) is constructed, leveraging the perception of the Earth's curvature to deepen the understanding of spatial relationships and geographic information. Experimental results demonstrate that our proposed method outperforms existing ship trajectory prediction techniques, showing enhanced reliability in multi-step predictions. [ABSTRACT FROM AUTHOR]

The goal of cross-view image based geo-localization is to determine the location of a given street-view image by matching it with a collection of geo-tagged aerial images, which has important applications in the fields of remote sensing information utilization and augmented reality. Most current cross-view image based geo-localization methods focus on the image content and ignore the relations between feature nodes, resulting in insufficient mining of effective information. To address this problem, this study proposes feature relation guided cross-view image based geo-localization. This method first processes aerial remote sensing images using a polar transform to achieve the geometric coarse alignment of ground-to-aerial images, and then realizes local contextual feature concern and global feature correlation modeling of the images through the feature relation guided attention generation module designed in this study. Specifically, the module includes two branches of deformable convolution based multiscale contextual feature extraction and global spatial relations mining, which effectively capture global structural information between feature nodes at different locations while correlating contextual features and guiding global feature attention generation. Finally, a novel feature aggregation module, MixVPR, is introduced to aggregate global feature descriptors to accomplish image matching and localization. After experimental validation, the cross-view image based geo-localization algorithm proposed in this study yields results of 92.08%, 97.70%, and 98.66% for the top 1, top 5, and top 10 metrics, respectively, in CVUSA, a popular public cross-view dataset, and exhibits superior performance compared to algorithms of the same type. [ABSTRACT FROM AUTHOR]

The improved generalized sidelobe canceller (GSC) based on eigenvalue decomposition beamforming technique for ultrasound imaging is proposed. Firstly, the signal subspace is obtained by performing eigenvalue decomposition on the covariance matrix of received data. Secondly, the weighting vector of GSC is divided into adaptive and non-adaptive two parts. Then the non-adaptive part is projected into the signal subspace to obtain a new steer vector. Subsequently, based on the orthogonal complementary space of the new steer vector, the blocking matrix is constructed. Finally, the weighting vector is updated by projecting the final weighting vector into the signal subspace. In order to verify the proposed algorithm, the simulations of the point targets and the cyst phantom were conducted in Field II. The experimental results indicate that the proposed method has better resolution and contrast ratio than the conventional algorithms. In addition, the algorithm is robust to noises. Furthermore, combining with coherence factor, the contrast ratio of the proposed algorithm can be further improved in comparison with a conventional GSC with coherence factor. [ABSTRACT FROM AUTHOR]

As an effective way to control springback, compensation technology is widely used in the field of automotive panel stamping. It is hard to reconstruct the whole tool mesh model containing addendum surface and binder surface in the compensation process, because the springback calculation is always carried out after trimming. A method for reconstructing the whole tool mesh automatically during springback compensation is proposed in this study. The method is based on the Displacement Adjustment (DA) compensation, and in the reconstructing process the blank mesh is split into two parts: the trimmed product and the addendum surface in trimming process. Base on this method, the changes of the reconstructed tool mesh can be avoided to ensure the accurate description of the tool surface. The reconstructed whole tool mesh can be used not only for the following stamping simulation but also for the springback compensation of automotive stamping parts. [ABSTRACT FROM AUTHOR]