27 October 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Synthetic aperture radar (SAR) has emerged as a critical technology for detecting and classifying objects such as ships in challenging environments. However, few-shot learning remains challenging due to the limited availability of labeled SAR data, complex radar backscatter, and variations in imaging parameters. In this paper, we propose a novel network, scattering point topology for few-shot ship classification (SPT-FSC), which addresses these challenges by incorporating scattering characteristics into the network learning process through a scattering point topology (SPT) based on scattering key points. We design a topology encoding branch (TEB) through a series of operations to encode the topological information of scattering points, resulting in a SPT embedding that improves the network's adaptability to the imaging mechanism and reduces imaging variability in SAR images. To effectively fuse the SPT embedding and image features extracted from a convolutional neural network (CNN), we introduce a novel mechanism named reciprocal feature fusion attention (RFFA). Additionally, to address the limited diversity in the training data, we apply fine-tuning based methodologies and construct a fine-grained ship classification dataset by combining the OpenSARShip and FUSAR-Ship datasets. Our comprehensive experiments on these datasets demonstrate the effectiveness of our proposed SPT-FSC method, achieving high accuracy and robustness in few-shot ship classification tasks for SAR images, outperforming existing methods in this domain.
7 February 2025 in IEEE Access
Accurate trajectory prediction and intention recognition are essential for effective decision-making, as different intents manifest in distinct trajectory patterns. This study focuses on trajectory prediction and intention recognition for airborne moving targets by proposing an integrated approach that leverages trajectory data for both tasks. Separate models were developed for trajectory prediction and intention recognition, with the trajectory prediction outcomes subsequently applied to enhance the accuracy of intention recognition. The proposed multi-channel parallel GRU-CNN neural network combines the temporal analysis capabilities of GRU with the spatial feature extraction strengths of CNN through a weight allocation strategy. This model achieved a notable performance, with a Mean Absolute Error (MAE) not exceeding 6.877. Additionally, a trajectory sequence similarity assessment system was constructed by incorporating Dynamic Time Warping (DTW), Hausdorff Distance (HD), and rate of altitude change, facilitating the classification of trajectories with similar intents. The integration of trajectory prediction into intention recognition significantly improved accuracy, as demonstrated by experimental results showing an accuracy rate exceeding 82%. These findings validate the effectiveness of the proposed method and offer an innovative technical solution for intention recognition of airborne moving targets.
6 July 2026 in Expert Systems with Applications