Ship detection in synthetic aperture radar (SAR) images is an important and challenging work in the field of image processing. Traditional detection algorithms usually rely on handmade features or predefined thresholds, the different performance is obtained with varying degrees of prior knowledge, and it is difficult to take advantage of big data. Recently, deep learning algorithms have found wide applications in ship detection from SAR images. However, due to the complex backgrounds and multiscale ships, it is hard for deep networks to extract representative target features, which limits the ship detection performance to a certain extent. In order to tackle the above problems, we propose an improved YOLOv4 (ImYOLOv4) based on attention mechanism. Firstly, to achieve the best trade-off between detection accuracy and speed, we adopt the off-the-shelf YOLOv4 as our basic framework because of its fast detection speed. Secondly, a thresholding attention module (TAM) is introduced to suppress the adverse effect of complex backgrounds and noises. Besides, we embed channel attention module (CAM) into improved BiFPN as the feature pyramid network (FPN) to better enhance the discrimination of the multiscale target features. Finally, the decoupled head with two parallel branches improves the performance of classification and regression. The proposed method is evaluated on public SAR dataset and the experimental results demonstrate that it has higher efficiency and feasibility than other mainstream methods, yielding the accuracy of 94.16% at intersection over union of 0.5 and 58.19% at intersection over union of 0.75.

In the field of autofocus for optical systems, although passive focusing methods are widely used due to their cost-effectiveness, fixed focusing windows and evaluation functions in certain scenarios can still lead to focusing failures. Additionally, the lack of datasets limits the extensive research of deep learning methods. In this work, we propose a neural network autofocus method with the capability of dynamically selecting the region of interest (ROI). Our main work is as follows: first, we construct a dataset for automatic focusing of grayscale images; second, we transform the autofocus issue into an ordinal regression problem and propose two focusing strategies: full-stack search and single-frame prediction; and third, we construct a MobileViT network with a linear self-attention mechanism to achieve automatic focusing on dynamic regions of interest. The effectiveness of the proposed focusing method is verified through experiments, and the results show that the focusing MAE of the full-stack search can be as low as 0.094, with a focusing time of 27.8 ms, and the focusing MAE of the single-frame prediction can be as low as 0.142, with a focusing time of 27.5 ms.

Ship detection in infrared images has found wide applications in both civil and military fields. Nowadays, infrared ship images serve as an irreplaceable information source for marine surveillance tasks due to the all-day and all-weather imaging capabilities of infrared sensors. However, previous research in optical and synthetic aperture radar images cannot be simply applied to ship detection in infrared images; there are multiscale ship targets in infrared datasets, especially small-sized targets with dense distributions. Besides, the complex surroundings, including inshore buildings and thick clouds, put higher difficulties for ship detection tasks. In order to handle the above problems, we propose a refined anchor-free model with feature enhancement mechanism for ship detection in infrared images. First, we redesign the network of YOLOv8 as the anchor-free detection model, aiming to perform the best multiscale detection accuracy and running speed. Secondly, a multiattention fusion module based on convolution kernels with different sizes is embedded into the backbone to distinguish the spatial salience of the targets from the complex surroundings. Besides, for improving precision in multiscale ship detection task, we propose the refined feature alignment and label assignment redesign modules, the former is used during the feature fusion process to cope with the problem of contextual misalignment, and the latter is introduced to refrain from the disadvantageous effect of the fuzzy areas in the process of model training. Experiments are conducted to evaluate the detection accuracy of the proposed model on the public infrared datasets ISDD, which proves the model's superiority over the state-of-the-art detection models for the ship detection task in infrared images.

Ship detection in synthetic aperture radar (SAR) images has gained great attention in civil and military fields. Anchor-based detection algorithms usually rely on preset candidate boxes, and a large amount of anchor boxes with different sizes will result in a large amount of computing resources being consumed. Recently, anchor-free algorithms have found wide applications in ship detection from SAR images. However, there are still some problems which limit the ship detection performance to a certain extent, such as how to effectively fuse salient features and unbalanced distribution of positive samples. In order to tackle the above problems, we propose a novel anchor-free model named SFF-YOLOX with salient feature fusion (SFF) mechanism. Firstly, we redesign the network of YOLOX to obtain the best balance between detection accuracy and running speed. Secondly, a saliency region extraction (SRE) module is introduced to generate the corresponding salient guide map of the input image. Besides, the SFF mechanism is proposed by fusing deep features and salient features to better enhance the discrimination of the multiscale targets. Finally, we improve the SimOTA mechanism by combining the predicted IoUs (intersection over union) and the anchor IoUs to the ground truth bounding boxes to instruct label assignment. We evaluate the detection accuracy and running speed of SFF-YOLOX on the public dataset SSD and test the generalization ability on HRSID and two complex large-scale SAR images, the experimental results prove the model's effectiveness for ship detection task in SAR images.