In the complex remote sensing image detection, there are still many challenges in maritime ship detection. This paper combines the latest swin-transformer model with satellite remote sensing big data, uses the SSDD dataset, researches for maritime ship target detection, realizes the target detection support for SSDD dataset, at the same time, this paper proposes an improved version of augmix method Multiple-augmix, based on the principle of data enhancement for SAR image dataset, is proposed to achieve target detection and data enhancement for SSDD dataset and make comparison experiments. The detection accuracy of swin-transformer can reach 86.5% for the original SSDD dataset, and 96.2% for the SSDD dataset enhanced with Multiple-augmix method, which is 10 percentage points higher than that before enhancement, and at the same time, by conducting experiments with Fasterrcnn, RetinaNet and Focos algorithms and making comparisons, the experiments prove that This framework can achieve high detection accuracy in remote sensing image detection, and the Multiple-augmix method proposed in this paper is very effective in improving the detection accuracy of SSDD dataset. In addition, we verify the effectiveness, stability and accuracy of the above algorithm for SAR image target detection in complex remote sensing scenarios.
Ship detection in synthetic aperture radar (SAR) images plays an important role in remote sensing, but it is still full of challenges in the deep learning area. The primary problem is that ships in SAR images have different sizes and orientations. The off-the-shelf detectors are not able to adapt to the situation. Recurrent feature pyramid networks are presented to detect ships with different sizes especially the small ones. Rotatable region proposal network is used for locating ships with a tighter rectangle. Rotatable anchors with sizes, aspect ratios, and angles are designed according to the distribution of ships in dataset. Multiratio region-of-interest pooling is used for projecting arbitrary-oriented proposals to fixed length vectors. Angle-related intersection-of-unit (ArIoU) is used for evaluating the intersection of rotatable proposals. ArIoU can be an indicator for nonmaximum suppression (NMS) and also is used for preparing negative and positive proposals. A loss function is proposed to compute loss between bounding boxes. The sinusoidal function is used for solving the problem of unstable angle. We also use a dataset called SSDD+ (SAR ship detection dataset plus) to evaluate different methods. Experiments based on SSDD+ show that our method achieves state-of-the-art performance. The dataset and the code will be public at https://zhuanlan.zhihu.com/p/143794468.
Ship classification in synthetic aperture radar (SAR) images is essential in remote sensing but still full of challenges in the deep learning era. The unbalanced dataset and lack of models are two limitations. Upsampling with data augmentation and ratio batching are proposed to solve the first problem. Upsampling with data augmentation is upsampling by cropping and flipping. It can improve the diversity of the dataset. Ratio batching is realized by choosing the same amount of ships per class in each minibatch. It can make the model converge faster and better. To solve the second problem, a new loss function and convolutional neural network model are proposed. The new loss function can maximize the intraclass compactness and interclass separation simultaneously. Dense residual network has two submodules. One is the identity mapping through elementwise summation to reuse old features. The other is dense connection through concatenation to exploit new features. The designed architecture is suitable for the task of SAR ship classification. We use the confusion matrix and accuracy averaged on classes to measure the performance. From the experiments, we can find that the proposed ideas have excellent performance especially on the rare classes.
Considering the sparseness of scatterers in the scene of a synthetic aperture radar (SAR) image, we propose a modified model for SAR images with enhanced features by automatically choosing variable lk-norm and regularization parameter. The approach is based on a regularized reconstruction of the scattering field, which employs prior information of the region of interest. It leads to an alternating iterative algorithm for the modeling. The method is constructed based on variable lk-norm and regularization parameter. Here, k is a function of the imaged region and it could be estimated during the iteration process to the scattering field. The regularization parameter is changing because it is being determined by k. Moreover, the parameter estimators of the presented model are derived by applying the method of log cumulants-based on Mellin transform. Compared to conventional SAR regularization methods, the proposed method reconstructs images with increased resolution, reduced clutter, and reduced computation cost. We demonstrate the performance of the method on real SAR scenes. The experiment results of measured SAR data prove the effectiveness.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.