Accurate and automated retinal vessel segmentation is essential for performing diagnosis and surgical planning of retinal diseases. However, conventional U-shaped networks often suffer from segmentation errors when dealing with fine and low-contrast blood vessels due to the loss of continuous resolution in the encoding stage and the inability to recover the lost information in the decoding stage. To address this issue, this paper introduces an effective full-resolution retinal vessel segmentation network, namely FRD-Net, which consists of two core components: the backbone network and the multi-scale feature fusion module (MFFM). The backbone network achieves horizontal and vertical expansion through the interaction mechanism of multi-resolution dilated convolutions while preserving the complete image resolution. In the backbone network, the effective application of dilated convolutions with varying dilation rates, coupled with the utilization of dilated residual modules for integrating multi-scale feature maps from adjacent stages, facilitates continuous learning of multi-scale features to enhance high-level contextual information. Moreover, MFFM further enhances segmentation by fusing deeper multi-scale features with the original image, facilitating edge detail recovery for accurate vessel segmentation. In tests on multiple classical datasets,compared to state-of-the-art segmentation algorithms, FRD-Net achieves superior performance and generalization with fewer model parameters.
Ground-based solar telescopes often encounter cloud interference during observations, leading to varying degrees of cloud cover in solar images. Existing cloud removal methods face several challenges, including incomplete cloud removal, insufficient restoration of solar features, and ineffectiveness against severe cloud cover. This paper proposes a novel deep learning-based approach for cloud removal and feature restoration in Hα full-disk solar images. First, to create a high-quality data set of cloud-covered images, we developed a method for detecting and classifying cloudiness in Hα full-disk solar images. This method correlates average intensity profiles in log-polar coordinates and utilizes the median pixel intensity in the images. Using this approach, we constructed a data set with three levels of cloudiness: mild, moderate, and severe, utilizing high-cadence Hα full-disk solar images from different sites within the Global Oscillation Network Group. Second, our cloud removal network employs an encoder–decoder structure, integrating the Res2Net module into the encoder to capture comprehensive solar image features. The decoder enhances the model's ability to extract semantic information about cloud-covered areas through a residual multiscale attention mechanism. Quantitative and qualitative experimental results demonstrate that the proposed method effectively removes complex cloud interference while preserving solar features, significantly improving the quality of observed data and outperforming existing solar image cloud removal methods. Additionally, the model serves as a valuable reference for removing clouds from other ground-based telescope data. The data and code are available on GitHub (https://github.com/dupeng24/full-disk-cloud-removal) under a CC0 1.0 License, and version 2.0 is archived in Zenodo (10.5281/zenodo.14184221).
Video stabilization plays a pivotal role in enhancing video quality by eliminating unwanted jitter in shaky videos. This paper introduces a novel video stabilization algorithm that leverages low‐rank constraint and trajectory optimization to effectively eliminate undesirable motion and generate stabilized videos. In the proposed algorithm, a low‐rank constraint regularization term is incorporated to enhance the smoothness of motion trajectories. Additionally, a predictive path smoothness term is integrated to ensure the consistency of motion across neighbouring frames. To address the problem of excessive cropping resulting from aggressive smoothing, a flexible local window strategy that emphasizes local motion relationships within the trajectories is introduced. The experimental results show that, compared to other excellent video stabilization algorithms, the proposed algorithm improves the stability metric by approximately 2.3%. Furthermore, in the stabilized videos generated by the algorithm, an approximate improvement of 2.18 dB in average image temporal fidelity and a 5.7% increase in average structural similarity between adjacent frames are achieved. The code that implements the proposed method is publicly accessible at https://github.com/CZS0319/VS_Low‐Rank_Constraint_Trajectory_Optimization .