Abstract Whole brain segmentation from magnetic resonance images (MRI) is crucial in diagnosing brain diseases and analyzing neuroimaging data. Despite advances through deep learning, challenges such as uneven gray distribution and the presence of artifacts still present hurdles in medical image processing. These limitations are often a result of insufficient spatial contextual information and lack of attention to important regions within existing models. To address these issues, this paper presents SSA‐UNet (Squeeze‐and‐Excitation and Self‐Attention UNet), a uniquely designed deep convolutional neural network that integrates spatial constraints by converting three consecutive 2D MRI slices into a single 2.5D image. This facilitates capturing inter‐slice dependencies effectively. Additionally, the newly formulated SSA block, which sequentially incorporates channel attention and Self‐Attention mechanisms, is placed before the decoders in the conventional U‐Net architecture. This enables the network to automatically weight different feature maps and focus more effectively on regions requiring precise segmentation. Rigorous evaluations on LPBA40 and IBSR18 datasets substantiate the remarkable improvements in accuracy and stability achieved by SSA‐UNet. Results indicate Dice coefficients of 98.38% and 97.47%, specificity of 99.69% and 99.57%, and sensitivity of 98.5% and 97.98% for the respective datasets. Compared to other existing models, SSA‐UNet shows significant improvements on both the LPBA40 and IBSR18 datasets. On the LPBA40 dataset, SSA‐UNet's Dice coefficient improved by 0.33% compared to the sub‐optimal model, while on the IBSR18 dataset, the improvement reached 1.78%. These empirical findings demonstrate SSA‐UNet's heightened capability in addressing the long‐standing challenges in MRI‐based whole‐brain segmentation.

Even though optical flow approaches based on convolutional neural networks have achieved remarkable performance with respect to both accuracy and efficiency, large displacements and motion occlusions remain challenges for most existing learning-based models. To address the abovementioned issues, we propose in this paper a self-attention-based multiscale feature learning optical flow computation method with occlusion feature map prediction. First, we exploit a self-attention mechanism-based multiscale feature learning module to compensate for large displacement optical flows, and the presented module is able to capture long-range dependencies from the input frames. Second, we design a simple but effective self-learning module to acquire an occlusion feature map, in which the predicted occlusion map is utilized to correct the optical flow estimation in occluded areas. Third, we explore a hybrid loss function that integrates the photometric and smoothness losses into the classical endpoint error (EPE)-based loss to ensure the accuracy and robustness of the presented network. Finally, we compare the proposed method with some state-of-the-art approaches using the MPI-Sintel and KITTI test databases. The experimental results demonstrate that the proposed method achieved competitive performance with respect to both accuracy and robustness, and it produced the better results compared to other methods under large displacements and motion occlusions.

In this paper, we propose a robust non-local TV-$L^{1}$optical flow method with occlusion detection to address the problem of weak robustness of optical flow estimation with motion occlusion. First, a TV-$L^{1}$form for flow estimation is defined using a combination of the brightness constancy and gradient constancy assumptions in the data term and by varying the weight under the Charbonnier function in the smoothing term. Second, to handle the potential risk of the outlier in the flow field, a general non-local term is added in the TV-$L^{1}$optical flow model to engender the typical non-local TV-$L^{1}$form. Third, an occlusion detection method based on triangulation is presented to detect the occlusion regions of the sequence. The proposed non-local TV-$L^{1}$optical flow model is performed in a linearizing iterative scheme using improved median filtering and a coarse-to-fine computing strategy. The results of the complex experiment indicate that the proposed method can overcome the significant influence of non-rigid motion, motion occlusion, and large displacement motion. Results of experiments comparing the proposed method and existing state-of-the-art methods by, respectively, using Middlebury and MPI Sintel database test sequences show that the proposed method has higher accuracy and better robustness.

High-resolution synthetic aperture radar (SAR) data have been widely used in marine environmental protection, marine environmental monitoring, and marine traffic management. Ship detection is one of the important parts of SAR data for marine applications. This letter focuses on the feature analysis of ships in high-resolution SAR images and proposes an improved optimizing algorithm for ship detection. A fast block detector is designed to extract sea clutter in a uniform local area, and then a constant false alarm rate detector is employed. Based on the kernel density estimation of ships, aspect ratio, and pixel points, ships are identified. TerraSAR-X and COSMO-SkyMed images are used to test our algorithm. The experimental results show that this algorithm can be implemented with time-saving, high-precision ship extraction, feature analysis, and detection.

Ship monitoring has a wide range of applications in marine activities and maritime management. Spaceborne synthetic aperture radar (SAR) technology has an advantage in ship detection over a vast region compared to other technologies. Recently, high-resolution SAR satellites have made ship recognition and classification possible from space. In July 2010, a ship recognition campaign was performed in the East China Sea. In situ investigation of ship types was carried out during the periods when the Italian COSMO-SkyMed satellites passed over the test site. Automatic Identification System (AIS) information was collected. Based on this information, a novel hierarchical ship classifier for COSMO-SkyMed SAR data was proposed. A total of 41 ship chips were cut from the SAR images for later classification. After preprocessing of the ship chips, geometric and backscattering characteristics of various ship types were analyzed. The ships were classified into bulk carriers, container ships, and oil tankers, with an accuracy of 93.3%, 80.0%, and 72.7%, respectively. Further investigation of the backscattering features with various illumination conditions is still in progress.

Ship detection is an important application of global monitoring of ocean environment and maritime traffic. Synthetic aperture radar (SAR) systems are active sensors offering unique good spatial resolution regardless of weather or other conditions. It has been widely used for ship detection. An improved ship detection for high resolution SAR images based on the ship feature confidence is proposed in this paper. The features include kernel density estimation, length-width ratio and the number of target pixels. Targets with high feature confidence will be interpreted as ships. The COSMO-SkyMed SAR image is adopted for investigating the proposed algorithm. Experiment results illustrate that the method can achieve good performances.