A synthetic aperture radar (SAR) image is crucial for ship detection in computer vision. Due to the background clutter, pose variations, and scale changes, it is a challenge to construct a SAR ship detection model with low false-alarm rates and high accuracy. Therefore, this paper proposes a novel SAR ship detection model called ST-YOLOA. First, the Swin Transformer network architecture and coordinate attention (CA) model are embedded in the STCNet backbone network to enhance the feature extraction performance and capture global information. Second, we used the PANet path aggregation network with a residual structure to construct the feature pyramid to increase global feature extraction capability. Next, to cope with the local interference and semantic information loss problems, a novel up/down-sampling method is proposed. Finally, the decoupled detection head is used to achieve the predicted output of the target position and the boundary box to improve convergence speed and detection accuracy. To demonstrate the efficiency of the proposed method, we have constructed three SAR ship detection datasets: a norm test set (NTS), a complex test set (CTS), and a merged test set (MTS). The experimental results show that our ST-YOLOA achieved an accuracy of 97.37%, 75.69%, and 88.50% on the three datasets, respectively, superior to the effects of other state-of-the-art methods. Our ST-YOLOA performs favorably in complex scenarios, and the accuracy is 4.83% higher than YOLOX on the CTS. Moreover, ST-YOLOA achieves real-time detection with a speed of 21.4 FPS.

Infrared (IR) small target detection against complex backgrounds is one of the most important tasks in infrared search and tracking systems. Achieving a high detection rate and a low false alarm rate against complex backgrounds remains challenging in practical applications. In this letter, we propose a novel small target detection method based on a local hypergraph dissimilarity measure (LHDM). As an alternative to the unstable dissimilarity in conventional simple graphs, a novel probabilistic hypergraph dissimilarity is presented to capture high-order affinity relationships among neighbors. Then, the corresponding LHDM in a local nested window is constructed based on the hypergraph model to enhance small targets and suppress complex backgrounds. The final saliency map is calculated via max-pooling of the LHDM at multiple scales. Finally, we utilize an adaptive threshold for target segmentation. The results of a series of experiments and evaluations performed on six real IR sequences demonstrate that the LHDM performs favorably compared to several baseline methods.

Cross-view geolocalization of unmanned aerial vehicles (UAVs) is a challenging task due to the positional discrepancies and uncertainties in scale and distance between UAVs and satellite views. Existing transformer-based geolocalization methods mainly use encoders to mine image contextual information. However, these methods have some limitations when dealing with scale changes in cross-view images. Therefore, we present an effective transformer-based Siamese network tailored for UAV geolocalization, called GeoFormer. First, an efficient transformer feature extraction network was designed, which utilizes linear attention to reduce the computational complexity and improve the computational efficiency of the network. Among them, we designed an efficient separable perceptron module based on depthwise separable convolution, which can effectively reduce the computational cost while improving the feature representation of the network. Second, we proposed a multiscale feature aggregation module, which deeply fuses salient features at different scales through a feedforward neural network to generate global feature representations with rich semantics, which improves the model's ability to capture image details and represent robust features. Additionally, we designed a semantic-guided region segmentation module, which utilizes a k -modes clustering algorithm to divide the feature map into multiple regions with semantic consistency and performs feature recognition within each semantic region to improve the accuracy of image matching. Finally, we designed a hierarchical reinforcement rotation matching strategy to achieve accurate UAV geolocalization based on the retrieval results of UAV view query satellite images using SuperPoint keypoints extraction and LightGlue rotation matching. According to the experimental results, our method effectively achieves UAV geolocalization.

In this article, we propose an effective infrared and visible image fusion network based on contrastive learning, which is called CLF-Net. A novel noise contrastive estimation framework is introduced into the image fusion to maximize mutual information between the fused image and source images. First, an unsupervised contrastive learning framework is constructed to promote fused image selectively retaining the most similar features in local areas of different source images. Second, we design a robust contrastive loss based on the deep representations of images, combining with the structural similarity loss to effectively guide the network in extracting and reconstructing features. Specifically, based on the deep representation similarities and structural similarities between the fused image and source images, the loss functions can guide the feature extraction network in adaptively obtaining the salient targets of infrared images and background textures of visible images. Then, the features are reconstructed in the most appropriate manner. In addition, our method is an unsupervised end-to-end model. All of our methods have been tested on public datasets. Based on extensive qualitative and quantitative analysis results, it has been demonstrated that our proposed method performs better than the existing state-of-the-art fusion methods.