Remote Sensing Micro-Object Detection under Global and Local Attention Mechanism

Small and dim target detection is a critical challenge in hyperspectral remote sensing, particularly in complex, large-scale scenes where spectral variability across diverse land cover types complicates the detection process. In this paper, we propose a novel target reasoning algorithm named Adaptive Global Dense Nested Reasoning Network (AGDNR). This algorithm integrates spatial, spectral, and domain knowledge to enhance the detection accuracy of small and dim targets in large-scale environments and simultaneously enables reasoning about target categories. The proposed method involves three key innovations. Firstly, we develop a high-dimensional, multi-layer nested U-Net that facilitates cross-layer feature transfer, preserving high-level features of small and dim targets throughout the network. Secondly, we present a novel approach for computing physicochemical parameters, which enhances the spectral characteristics of targets while minimizing environmental interference. Thirdly, we construct a geographic knowledge graph that incorporates both target and environmental information, enabling global target reasoning and more effective detection of small targets across large-scale scenes. Experimental results on three challenging datasets show that our method outperforms state-of-the-art approaches in detection accuracy and achieves successful classification of different small targets. Consequently, the proposed method offers a robust solution for the precise detection of hyperspectral small targets in large-scale scenarios.

In recent years, with the development of deep learning, machine translation using neural network has gradually become the mainstream method in industry and academia. The existing Chinese-English machine translation models generally adopt the deep neural network architecture based on attention mechanism. However, it is still a challenging problem to model short and long sequences simultaneously. Therefore, a bidirectional LSTM model integrating attention mechanism is proposed. Firstly, by using the word vector as the input data of the translation model, the linguistic symbols used in the translation process are mathematized. Secondly, two attention mechanisms are designed: local attention mechanism and global attention mechanism. The local attention mechanism is mainly used to learn which words or phrases in the input sequence are more important for modeling, while the global attention mechanism is used to learn which layer of expression vector in the input sequence is more critical. Bidirectional LSTM can better fuse the feature information in the input sequence, while bidirectional LSTM with attention mechanism can simultaneously model short and long sequences. The experimental results show that compared with many existing translation models, the bidirectional LSTM model with attention mechanism can effectively improve the quality of machine translation.

In the realm of unmanned aerial vehicles, we proposed an enhanced small target detection algorithm, MGAC-YOLO, to address the challenges of missed detections and low accuracy associated with small target identification. Initially, we designed the MConv (Multi-layer Convolution) module to replace the conventional Conv module within the backbone network, thereby augmenting the dimensionality of information capture and enhancing the detection performance for small targets. Subsequently, we harnessed the advantages of both attention mechanisms-GAM (Global Attention Mechanism) and CloAttention (Contextualized Local and Global Attention)-to create a GACAttention module that extracts small target features from both global and local perspectives, thereby enriching the network's focus on small target feature information and further enhancing its feature processing capabilities. Finally, we incorporated an additional small target detection layer to capture feature information at a shallower level, thereby reducing the likelihood of missed detections and bolstering the detection capabilities for small targets. Experimental results on the VisDrone2019 dataset demonstrate that the Precision, mAP50, and mAP50-95 of the MGAC-YOLO algorithm have improved by 5.3%, 6.3%, and 4.4%, respectively, in comparison to the baseline model YOLOv8s. Furthermore, when compared to other leading algorithms, the MGAC-YOLO algorithm has exhibited notable superiority.

This study focuses on advancing the field of remote sensing image target detection, addressing challenges such as small target detection, complex background handling, and dense target distribution. We propose solutions based on enhancing the YOLOv7 algorithm. Firstly, we improve the multi-scale feature enhancement (MFE) method of YOLOv7, enhancing its adaptability and precision in detecting small targets and complex backgrounds. Secondly, we design a modified YOLOv7 global information DP-MLP module to effectively capture and integrate global information, thereby improving target detection accuracy and robustness, especially in handling large-scale variations and complex scenes. Lastly, we explore a semi-supervised learning model (SSLM) target detection algorithm incorporating unlabeled data, leveraging information from unlabeled data to enhance the model’s generalization ability and performance. Experimental results demonstrate that despite the outstanding performance of YOLOv7, the mean average precision (MAP) can still be improved by 1.9%. Specifically, under testing on the TGRS-HRRSD-Dataset, the MFE and DP-MLP models achieve MAP values of 93.4% and 93.1%, respectively. Across the NWPU VHR-10 dataset, the three models achieve MAP values of 93.1%, 92.1%, and 92.2%, respectively. Significant improvements are observed across various metrics compared to the original model. This study enhances the adaptability, accuracy, and generalization of remote sensing image object detection.

Vehicle detection is an important technology in au-tonomous driving, for which high detection accuracy and real-time performance are often required. The YOLOv5-GE vehicle detection algorithm is proposed to address the situation that the YOLOv5 vehicle detection model has false detection and missed detection for small and dense targets in complex environments. The global attention mechanism is added to the backbone net-work of the YOLOOv5 model, which is composed of two inde-pendent submodules of channel attention and convolutional spa-tial attention, which prevents the loss of information to a certain extent and amplifies the interaction of global dimensions. Second-ly, the training process is optimized using the Focal-EloU loss function to replace the GloU loss function, which improves the accuracy of vehicle detection. Finally, the proposed YOLOv5-GE algorithm and the YOLOv5 algorithm are subjected to a con-trolled experiment on the KITTI dataset. The experimental re-sults show that the YOLOv5-GE algorithm achieves an average accuracy of 86% while maintaining real-time performance, which is 2.5% higher than that of the YOLOv5 algorithm, and can im-prove the detection accuracy of small and dense targets in com-plex environments.

Recent years have seen rapid progress in target-detection missions, whereas small targets, dense target distribution, and shadow occlusion continue to hinder progress in the detection of small targets, such as cars, in remote sensing images. To address this shortcoming, we propose herein a backbone feature-extraction network called “RepDarkNet” that adds several convolutional layers to CSPDarkNet53. RepDarkNet considerably improves the overall network accuracy with almost no increase in inference time. In addition, we propose a multi-scale cross-layer detector that significantly improves the capability of the network to detect small targets. Finally, a feature fusion network is proposed to further improve the performance of the algorithm in the AP@0.75 case. Experiments show that the proposed method dramatically improves detection accuracy, achieving AP = 75.53% for the Dior-vehicle dataset and mAP = 84.3% for the Dior dataset, both of which exceed the state-of-the-art level. Finally, we present a series of improvement strategies that justifies our improvement measures.

Infrared small target detection has become a research hotspot in recent years. Due to the small target size and low contrast with the background, it remains a highly challenging task. Existing infrared small target detection algorithms are generally implemented on 8-bit low dynamic range (LDR) images, whereas raw infrared sensing images typically possess a 14–16 bit high dynamic range (HDR). Conventional HDR image enhancement methods do not consider the subsequent detection task. As a result, the enhanced LDR images often suffer from overexposure, increased noise levels with higher contrast, and target distortion or loss. Consequently, discriminative features in HDR images that are beneficial for detection are not effectively exploited, which further increases the difficulty of small target detection. To extract target features under these conditions, existing detection algorithms usually rely on large parameter models, leading to an unsatisfactory trade-off between efficiency and accuracy. To address these issues, this paper proposes a novel infrared small target detection framework based on HDR image enhancement (HDR-IRSTD). Specifically, a multi-branch feature extraction and fusion mapping subnetwork (MFEF-Net) is designed to achieve the mapping from HDR to LDR. This subnetwork effectively enhances small targets and suppresses noise while preserving both detailed features and global information. Furthermore, considering the characteristics of infrared small targets, an asymmetric Vision Mamba U-Net with multi-level inputs (AVM-Unet) is developed, which captures contextual information effectively while maintaining linear computational complexity. During training, a bilevel optimization strategy is adopted to collaboratively optimize the two subnetworks, thereby yielding optimal parameters for both HDR infrared image enhancement and small target detection. Experimental results demonstrate that the proposed method achieves visually favorable enhancement and high-precision detection, with strong generalization ability and robustness. The performance and efficiency of the method exhibit a well-balanced trade-off.

Accurate detection of fresh jujube fruits plays a vital role in precision agriculture, enabling reliable yield estimation and supporting automation tasks such as robotic harvesting. To address the challenges of detecting such small targets (≤32 × 32 pixels) in complex orchard environments, this study proposes JFST-DETR, an efficient and robust detection model based on the Real-Time DEtection TRansformer (RT-DETR). First, to address the insufficient feature representation for small jujube fruit targets, a novel module called the Global Awareness Adaptive Module (GAAM) is designed. Building on GAAM and the innovative Spatial Coding Module (SCM), a new Spatial Enhancement Pyramid Network (SEPN) is proposed. Through the spatial-depth transformation domain and global awareness adaptive processing units, SEPN captures fine-grained features of small targets, enhancing the detection accuracy for small objects. Second, a Dynamic Sampling (DySample) operator is adopted, which optimizes feature space details via dynamic offset calculation and lightweight design, improving detection accuracy while reducing computational costs. Finally, to solve the problem of complex background interference caused by foliage occlusion and illumination variations, Pinwheel-Shaped Convolution (PSConv) is introduced. By using asymmetric padding and multi-directional convolution, PSConv enhances the robustness of feature extraction, ensuring reliable recognition in complex agricultural environments. Experimental results show that JFST-DETR achieves precision, recall, F1, mAP@50, and mAP@50:95 of 93%, 86.8%, 89.8%, 94.3%, and 75.2%. Compared to the baseline model, these metrics improve by 0.8%, 3.7%, 2.4%, 2.6%, and 3.1%, respectively. Cross-dataset evaluations further confirm its strong generalizability, demonstrating potential as a practical solution for small-target detection in intelligent horticulture.

Heterogeneous graph embedding by aggregating meta-path and meta-structure through attention mechanism

Research on Infrared Dim and Small Target Detection Algorithm Based on Low-Rank Tensor Recovery

With the rapid development of UAV and infrared imaging technology, the cost of UAV infrared imaging technology has decreased steadily. Small target detection technology in aerial infrared images has great potential for applications in many fields, especially in the field of traffic surveillance. Because of the low contrast and relatively limited feature information in infrared images compared to visible images, the difficulty involved in small road target detection in infrared aerial images has increased. To solve this problem, this study proposes a feature-enhanced attention and dual-GELAN net (FEADG-net) model. In this network model, the reliability and effectiveness of small target feature extraction is enhanced by a backbone network combined with low-frequency enhancement and a swin transformer. The multi-scale features of the target are fused using a dual-GELAN neck structure, and a detection head with the parameters of the auto-adjusted InnerIoU is constructed to improve the detection accuracy for small infrared targets. The viability of the method was proved using the HIT-UAV dataset and IRTS-AG dataset. According to a comparative experiment, the mAP50 of FEADG-net reached more than 90 percent, which was higher than that of any previous method and it met the real-time requirements. Finally, an ablation experiment was conducted to demonstrate that all three of the modules proposed in the method contributed to the improvement in the detection accuracy. This study not only designs a new algorithm for small road object detection in infrared remote sensing images from UAVs but also provides new ideas for small target detection in remote sensing images for other fields.

The infrared image in the sea background usually contains random noise, sea waves, fish scale light and other clutter. Sea waves and fish scale light interference are similar to small infrared targets, so it is difficult to eliminate such interference and detect small infrared targets quickly and accurately. In this paper, a small target detection method based on non-local similarity is proposed. The interference is eliminated by using the class feature similarity of interference and the overall feature uniqueness of the small target. Firstly, this paper performs filtering to remove random noise, and the suspected small targets can be extracted by executing Top Hat filtering. Secondly, a multi-feature vector is constructed for all suspected targets. Finally, this paper analyzes the characteristics of different interference and executes clustering step by step. The wave edge interference and fish scale light interference can be eliminated in turn. Feature threshold is set based on the interference that has been identified to obtain the true small infrared target according to the uniqueness of the characteristics of the true target. The experimental results show that compared with other small target detection algorithms, the proposed algorithm can detect small infrared targets in complex sea background effectively.

As a task in object detection, small object detection mainly focuses on detecting objects of small size, which is more complex than general object detection. It is pivotal in various applications, e.g., small tumor detection, national defense and security, and traffic surveillance. Small objects have low pixels, few effective features, and a large influence of background noise, making small object detection extremely challenging. Currently, most object detection algorithms fail to take advantage of global context information to improve accuracy. Moreover, the conventional bounding-box proposal generation method will cause the missed detection of small targets since the target features are few and challenging to locate. To address the above problems, this paper uses the position enhancement method to improve the proposals’ generation to improve the recall rate and accuracy rate of small object detection. First, the location enhancement module adds additional keypoint location supervision to obtain target latent keypoints. Besides, we propose a keypoint expansion method to get more accurate keypoint locations. A global contextual attention mechanism is further introduced, enabling the detector to learn fine-grained features with contextual location information better. The experimental results on two datasets show that the proposed method can significantly improve the accuracy and recall of small target detection.

The problems of low detection accuracy and high leakage rate of small targets on the water’s surface when observed from the viewpoint of an uncrewed ship are proposed to be resolved by an improved YOLOv7 detection algorithm. Firstly, the parameter-free attention mechanisms SimAM and PConv are introduced into the network to enhance the model’s feature extraction for small targets and reduce the number of model parameters, and SimAM and PConv in the backbone are combined with ELAN1 to form a new efficient layer aggregation network module ELAN1-SAPC. Then, the Head part of the model adopts the newly proposed MP-CXOS structure, which can enhance the model’s focus on small targets and effectively reduce the loss of small target feature information. Finally, the loss function is optimized by incorporating the new NWD metric approach to improve the model’s ability to detect small targets and speed up network convergence. The data set is also processed using data augmentation to improve the model’s generalization. The experiments show that compared with the basic model, the mean Average Precision of the improved YOLOv7 model increases by 5.3 per cent, the F1 score increases by 0.06, and the number of parameters decreases by 20.0 per cent. Therefore, the improved model has significantly improved detection performance and is more lightweight.

Dim and small infrared target fast detection guided by visual saliency