In view of the issues of missed and false detections encountered in small object detection for UAV remote sensing images, and the inadequacy of existing algorithms in terms of complexity and generalization ability, we propose a small object detection model named IA-YOLOv8 in this paper. This model integrates the intra-group multi-scale fusion attention mechanism and the adaptive weighted feature fusion approach. In the feature extraction phase, the model employs a hybrid pooling strategy that combines Avg and Max pooling to replace the single Max pooling operation used in the original SPPF framework. Such modifications enhance the model’s ability to capture the minute features of small objects. In addition, an adaptive feature fusion module is introduced, which is capable of automatically adjusting the weights based on the significance and contribution of features at different scales to improve the detection sensitivity for small objects. Simultaneously, a lightweight intra-group multi-scale fusion attention module is implemented, which aims to effectively mitigate background interference and enhance the saliency of small objects. Experimental results indicate that the proposed IA-YOLOv8 model has a parameter quantity of 10.9 MB, attaining an average precision (mAP) value of 42.1% on the Visdrone2019 test set, an mAP value of 82.3% on the DIOR test set, and an mAP value of 39.8% on the AI-TOD test set. All these results outperform the existing detection algorithms, demonstrating the superior performance of the IA-YOLOv8 model in the task of small object detection for UAV remote sensing.

In recent years, significant advances have been gained in visual detection, and an abundance of outstanding models have been proposed. However, state-of-the-art object detection networks have some inefficiencies in detecting small targets. They commonly fail to run on portable devices or embedded systems due to their high complexity. In this workpaper, a real-time object detection model, termed as Tiny Fast You Only Look Once (TF-YOLO), is developed to implement in an embedded system. Firstly, the k-means++ algorithm is applied to cluster the dataset, which contributes to more excellent priori boxes of the targets. Secondly, inspired by the multi-scale prediction idea in the Feature Pyramid Networks (FPN) algorithm, the framework in YOLOv3 is effectively improved and optimized, by three scales to detect the earlier extracted features. In this way, the modified network is sensitive for small targets. Experimental results demonstrate that the proposed TF-YOLO method is a smaller, faster and more efficient network model increasing the performance of end-to-end training and real-time object detection for a variety of devices.

This study proposes a novel approach for detecting weak small infrared (IR) targets, called double-image and double-local contrast measurement (DDLCM), designed to overcome challenges of low contrast and complex backgrounds in images. In this approach, the original image is decomposed into odd and even images, and the gray difference contrast is determined using a dual-neighborhood sliding window structure, enhancing target saliency and contrast by increasing the distinction between the target and the local background. A central unit is then constructed to capture relationships between neighboring and non-neighboring units, aiding in clutter suppression and eliminating bright non-target interference. Lastly, the output value is derived by extracting the lowest contrast value of the weak small targets from the saliency map in each direction. Experimental results on two datasets demonstrate that the DDLCM algorithm significantly enhances real-time IR dim target detection, achieving an average performance improvement of 32.83%. The area under the ROC curve (AUC) decline is effectively controlled, with a maximum reduction limited to 3%. Certain algorithms demonstrate a notable AUC improvement of up to 43.96%. To advance infrared dim target detection research, we introduce the IFWS dataset for benchmarking and validating algorithm performance.

In the rapidly evolving image processing domain, transformers have emerged as powerful tools, yet significant challenges are encountered when they are applied to underwater image enhancement, such as visual disparity and computational inefficiency. Transformers do not have a unique module to maintain their performance while reducing the number of parameters. This study addresses the gap in the literature by introducing the globally deformable selection transformer (GS-Transformer), which is a model designed to enhance global feature selection and pixel connectivity, thereby reducing the computational complexity of the model while maintaining the image processing effect. Our novel multiresolution encoder-decoder module explicitly incorporates global information, overcoming the limitations of traditional transformers, whereas the multilocal coherence preserving loss (MCPL) mechanism ensures content integrity and coherence. Compared with the latest transform-based underwater image algorithms, this method is 15 times faster and utilizes only 41.7% (or approximately a half less) of the number of parameters. The experimental results on the UIEB, EUVP, and Synthesize datasets reveal that GS-Transformer achieves state-of-the-art performance in underwater image enhancement, with a reduced parameter number and improved efficiency, representing a significant advancement in the field. Our research will promote the application of the transformer in scenarios with high real-time performance.

Intelligent fault diagnosis is of great significance to guarantee the safe operation of mechanical equipment. However, the widely used diagnosis models rely on sufficient independent and homogeneously distributed monitoring data to train the model. In practice, the available data of mechanical equipment faults are insufficient and the data distribution varies greatly under different working conditions, which leads to the low accuracy of the trained diagnostic model and restricts it, making it difficult to apply to other working conditions. To address these problems, a novel fault diagnosis method combining a generative adversarial network and transfer learning is proposed in this paper. Dummy samples with similar fault characteristics to the actual engineering monitoring data are generated by the generative adversarial network to expand the dataset. The transfer fault characteristics of monitoring data under different working conditions are extracted by a deep residual network. Domain-adapted regular term constraints are formulated to the training process of the deep residual network to form a deep transfer fault diagnosis model. The bearing fault data are used as the original dataset to validate the effectiveness of the proposed method. The experimental results show that the proposed method can reduce the influence of insufficient original monitoring data and enable the migration of fault diagnosis knowledge under different working conditions.

Spaceborne synthetic aperture radar (SAR) image ship detection is an important tool to ensure the safety of sea areas and improve the efficiency of maritime traffic. Due to the sparse distribution of ships in the vast ocean, many imaging results are redundant. Furthermore, SAR imaging consumes huge computing, storage, and communication resources. The range-compressed data, without azimuth compression calculation, has caught our attention. Nevertheless, the echo energy of the ship is scattered in the azimuth direction, making it difficult to detect. Several deep learning-based methods are proposed, yet their performance is constrained by labeled datasets. As they neglect sea clutter interference, these methods are also impractical. To address these issues, this paper proposes a constant false alarm rate (CFAR)-based ship detector for range-compressed SAR data. Firstly, the imaging process of spaceborne SAR signal is reviewed and analyzed. Then, a generalized Gamma distribution based sea clutter model is proposed for the SAR range focused domain. Next, a CFAR-based method for detecting ships in range-compressed SAR data is customized. Finally, experiments are conducted on Sentinel-1 and ERS-2 SAR data. The results show that the proposed sea clutter model has high goodness-of-fit, and the customized CFAR-based method effectively detects ship targets. In summary, ship detection in range-compressed SAR data is very promising research.