Search

Simple Summary: This study initially analyzed surveillance videos to identify and extract key moments of Andrias davidianus' parental care behavior and established a dataset for this behavior. Based on this, this study optimized the existing YOLOv8 object detection model specifically for this task and proposed the ML-YOLOv8 model, which shows outstanding performance in recognizing and analyzing A. davidianus' parental care behavior. Following testing and verification, the ML-YOLOv8 model demonstrated excellent performance in efficiently and accurately detecting A. davidianus' parental care behavior. The findings of this study not only provide evidence for optimizing breeding technology and conservation management of A. davidianus in their natural habitat but also offer new technical means and research ideas for studying amphibian behavioral ecology. Optimizing the breeding techniques and increasing the hatching rate of Andrias davidianus offspring necessitates a thorough understanding of its parental care behaviors. However, A. davidianus' nocturnal and cave-dwelling tendencies pose significant challenges for direct observation. To address this problem, this study constructed a dataset for the parental care behavior of A. davidianus, applied the target detection method to this behavior for the first time, and proposed a detection model for A. davidianus' parental care behavior based on the YOLOv8s algorithm. Firstly, a multi-scale feature fusion convolution (MSConv) is proposed and combined with a C2f module, which significantly enhances the feature extraction capability of the model. Secondly, the large separable kernel attention is introduced into the spatial pyramid pooling fast (SPPF) layer to effectively reduce the interference factors in the complex environment. Thirdly, to address the problem of low quality of captured images, Wise-IoU (WIoU) is used to replace CIoU in the original YOLOv8 to optimize the loss function and improve the model's robustness. The experimental results show that the model achieves 85.7% in the mAP50-95, surpassing the YOLOv8s model by 2.1%. Compared with other mainstream models, the overall performance of our model is much better and can effectively detect the parental care behavior of A. davidianus. Our research method not only offers a reference for the behavior recognition of A. davidianus and other amphibians but also provides a new strategy for the smart breeding of A. davidianus. [ABSTRACT FROM AUTHOR]

Cutting-edge detection is a critical step in mechanized rice harvesting. Through visual cutting-edge detection, an algorithm can sense in real-time whether the rice harvesting process is along the cutting-edge, reducing loss and improving the efficiency of mechanized harvest. Although convolutional neural network-based models, which have strong local feature acquisition ability, have been widely used in rice production, these models involve large receptive fields only in the deep network. Besides, a self-attention-based Transformer can effectively provide global features to complement the disadvantages of CNNs. Hence, to quickly and accurately complete the task of cutting-edge detection in a complex rice harvesting environment, this article develops a Transformer Convolution Network (TCNet). This cutting-edge detection algorithm combines the Transformer with a CNN. Specifically, the Transformer realizes a patch embedding through a 3 × 3 convolution, and the output is employed as the input of the Transformer module. Additionally, the multi-head attention in the Transformer module undergoes dimensionality reduction to reduce overall network computation. In the Feed-forward network, a 7 × 7 convolution operation is used to realize the position-coding of different patches. Moreover, CNN uses depth-separable convolutions to extract local features from the images. The global features extracted by the Transformer and the local features extracted by the CNN are integrated into the fusion module. The test results demonstrated that TCNet could segment 97.88% of the Intersection over Union and 98.95% of the Accuracy in the unharvested region, and the number of parameters is only 10.796M. Cutting-edge detection is better than common lightweight backbone networks, achieving the detection effect of deep convolutional networks (ResNet-50) with fewer parameters. The proposed TCNet shows the advantages of a Transformer combined with a CNN and provides real-time and reliable reference information for the subsequent operation of rice harvesting. [ABSTRACT FROM AUTHOR]

Current single-view image inpainting methods often suffer from low image information utilization and suboptimal repair outcomes. To address these challenges, this paper introduces a novel image inpainting framework that leverages a structure-guided multi-scale attention pyramid network. This network consists of a structural repair network and a multi-scale attention pyramid semantic repair network. The structural repair component utilizes a dual-branch U-Net network for robust structure prediction under strong constraints. The predicted structural view then serves as auxiliary information for the semantic repair network. This latter network exploits the pyramid structure to extract multi-scale features of the image, which are further refined through an attention feature fusion module. Additionally, a separable gated convolution strategy is employed during feature extraction to minimize the impact of invalid information from missing areas, thereby enhancing the restoration quality. Experiments conducted on standard datasets such as Paris Street View and CelebA demonstrate the superiority of our approach over existing methods through quantitative and qualitative comparisons. Further ablation studies, by incrementally integrating proposed mechanisms into a baseline model, substantiate the effectiveness of our multi-view restoration strategy, separable gated convolution, and multi-scale attention feature fusion. [ABSTRACT FROM AUTHOR]

In the field of Generalized Zero-Shot Learning (GZSL), the challenge lies in learning attribute-based information from seen classes and effectively conveying this knowledge to recognize both seen and unseen categories during the training process. This paper proposes an innovative approach to enhance the generalization ability and efficiency of GZSL models by integrating a Convolutional Block Attention Module (CBAM). The CBAM blends channel-wise and spatial-wise information to emphasize key features, thereby improving the model's discriminative and localization capabilities. Additionally, the method employs a ResNet101 backbone for systematic image feature extraction, enhanced contrastive learning, and a similarity map generator with attribute prototypes. This comprehensive framework aims to achieve robust visual–semantic embedding for classification tasks. The proposed method demonstrates significant improvements in performance metrics in benchmark datasets, showcasing its potential in advancing GZSL applications. [ABSTRACT FROM AUTHOR]

Full-thickness macular hole (FTMH) leads to central vision loss. It is essential to identify patients with FTMH at high risk of postoperative failure accurately to achieve anatomical closure. This study aimed to construct a predictive model for the anatomical outcome of FTMH after surgery. A retrospective study was performed, analyzing 200 eyes from 197 patients diagnosed with FTMH. Radiomics features were extracted from optical coherence tomography (OCT) images. Logistic regression, support vector machine (SVM), and backpropagation neural network (BPNN) classifiers were trained and evaluated. Decision curve analysis and survival analysis were performed to assess the clinical implications. Sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC) were calculated to assess the model effectiveness. In the training set, the AUC values were 0.998, 0.988, and 0.995, respectively. In the test set, the AUC values were 0.941, 0.943, and 0.968, respectively. The OCT-omics scores were significantly higher in the "Open" group than in the "Closed" group and were positively correlated with the minimum diameter (MIN) and base diameter (BASE) of FTMH. Therefore, in this study, we developed a model with robust discriminative ability to predict the postoperative anatomical outcome of FTMH. [ABSTRACT FROM AUTHOR]

To enable the timely adjustment of the control strategy of automobile active safety systems, enhance their capacity to adapt to complex working conditions, and improve driving safety, this paper introduces a new method for predicting road surface state information and recognizing road adhesion coefficients using an enhanced version of the MobileNet V3 model. On one hand, the Squeeze-and-Excitation (SE) is replaced by the Convolutional Block Attention Module (CBAM). It can enhance the extraction of features effectively by considering both spatial and channel dimensions. On the other hand, the cross-entropy loss function is replaced by the Bias Loss function. It can reduce the random prediction problem occurring in the optimization process to improve identification accuracy. Finally, the proposed method is evaluated in an experiment with a four-wheel-drive ROS robot platform. Results indicate that a classification precision of 95.53% is achieved, which is higher than existing road adhesion coefficient identification methods. [ABSTRACT FROM AUTHOR]

Building segmentation has extensive research value and application prospects in high-resolution remote sensing image (HRSI) processing. However, complex architectural contexts, varied building morphologies, and non-building occlusions make building segmentation challenging. Compared with traditional methods, deep learning-based methods present certain advantages in terms of accuracy and intelligence. At present, the most popular option is to first apply a single neural network to encode an HRSI, then perform a decoding process through up-sampling or using a transposed convolution operation, and then finally obtain the segmented building image with the help of a loss function. Although effective, this approach not only tends to lead to a loss of detail information, but also fails to fully utilize the contextual features. As an alternative, we propose a novel network called NPSFF-Net. First, using an improved pseudo-Siamese network composed of ResNet-34 and ResNet-50, two sets of deep semantic features of buildings are extracted with the support of transfer learning, and four encoded features at different scales are obtained after fusion. Then, information from the deepest encoded feature is enriched using a feature enhancement module, and the resolutions are recovered via the operations of skip connections and transposed convolutions. Finally, the discriminative features of buildings are obtained using the designed feature fusion algorithm, and the optimal segmentation model is obtained by fitting a cross-entropy loss function. Our method obtained intersection-over-union values of 89.45% for the Aerial Imagery Dataset, 71.88% for the Massachusetts Buildings Dataset, and 68.72% for the Satellite Dataset I. [ABSTRACT FROM AUTHOR]

Underwater images, as a crucial medium for storing ocean information in underwater sensors, play a vital role in various underwater tasks. However, they are prone to distortion due to the imaging environment, which leads to a decline in visual quality, which is an urgent issue for various marine vision systems to address. Therefore, it is necessary to develop underwater image enhancement (UIE) and corresponding quality assessment methods. At present, most underwater image quality assessment (UIQA) methods primarily rely on extracting handcrafted features that characterize degradation attributes, which struggle to measure complex mixed distortions and often exhibit discrepancies with human visual perception in practical applications. Furthermore, current UIQA methods lack the consideration of the perception perspective of enhanced effects. To this end, this paper employs luminance and saliency priors as critical visual information for the first time to measure the enhancement effect of global and local quality achieved by the UIE algorithms, named JLSAU. The proposed JLSAU is built upon an overall pyramid-structured backbone, supplemented by the Luminance Feature Extraction Module (LFEM) and Saliency Weight Learning Module (SWLM), which aim at obtaining perception features with luminance and saliency priors at multiple scales. The supplement of luminance priors aims to perceive visually sensitive global distortion of luminance, including histogram statistical features and grayscale features with positional information. The supplement of saliency priors aims to perceive visual information that reflects local quality variation both in spatial and channel domains. Finally, to effectively model the relationship among different levels of visual information contained in the multi-scale features, the Attention Feature Fusion Module (AFFM) is proposed. Experimental results on the public UIQE and UWIQA datasets demonstrate that the proposed JLSAU outperforms existing state-of-the-art UIQA methods. [ABSTRACT FROM AUTHOR]

Compared with general images, objects in remote sensing (RS) images typically exhibit a conspicuous diversity due to their arbitrary orientations. However, many of the prevalent detectors generally apply an inflexible strategy in setting the angles of anchor, ignoring the fact that the number of possible orientations is predictable. Consequently, their processes integrate numerous superfluous angular considerations and hinder their efficiency. To deal with this situation, we propose a dynamic density-driven estimation network (DDE-Net). We design three core modules in DDE-Net: a density-map and mask generation module (DGM), mask routing prediction module (MRM), and spatial-balance calculation module (SCM). DGM is designed for the generation of a density map and mask, which can extract salient features. MRM is for the prediction of object orientation and corresponding weights, which are used to calculate feature maps. SCM is used to affine transform the convolution kernel, which applies an adaptive weighted compute mechanism to enhance the average feature, so as to balance the spatial difference to the rotation feature extraction. A broad array of experimental evaluations have conclusively shown that our methodology outperforms existing state-of-the-art detectors on common aerial object datasets (DOTA and HRSC2016). [ABSTRACT FROM AUTHOR]

To address the problem that complex bearing faults are coupled to each other, and the difficulty of diagnosis increases, an improved envelope spectrum–maximum second-order cyclostationary blind deconvolution (IES-CYCBD) method is proposed to realize the separation of vibration signal fault features. The improved envelope spectrum (IES) is obtained by integrating the part of the frequency axis containing resonance bands in the cyclic spectral coherence function. The resonant bands corresponding to different fault types are accurately located, and the IES with more prominent target characteristic frequency components are separated. Then, a simulation is carried out to prove the ability of this method, which can accurately separate and diagnose fault types under high noise and compound fault conditions. Finally, a compound bearing fault experiment with inner and outer ring faults is designed, and the inner and outer ring fault characteristics are successfully separated by the proposed IES-CYCBD method. Therefore, simulation and experiments demonstrate the strong capability of the proposed method for complex fault separation and diagnosis. [ABSTRACT FROM AUTHOR]

This study addresses the issue of vortex current fields near the islands and reefs in China's straits, which pose significant challenges to engineering construction and navigation safety in the surrounding waters. To monitor these vortex fields, the study proposes an innovative method utilizing acoustic signals. The study utilizes the numerical simulation and phase feature extraction of acoustic signals in the vortex current field, based on ray acoustic theory and time-reversal mirror technology. The study successfully monitored the central position of the vortex core and characteristic radius of the vortex current field near Barley Straw Reef using HYCOM data for the first time. Furthermore, the performance of the method was analyzed under different acoustic phase perturbations and signal-to-noise ratios. The numerical simulation results demonstrate that the acoustic method is effective in monitoring near-shore vortex fields, and the time-reversal mirror technique is useful in extracting phase difference information from acoustic signals generated by vortex currents. [ABSTRACT FROM AUTHOR]

The compression method for wellbore trajectory data is crucial for monitoring wellbore stability. However, classical methods like methods based on Huffman coding, compressed sensing, and Differential Pulse Code Modulation (DPCM) suffer from low real-time performance, low compression ratios, and large errors between the reconstructed data and the source data. To address these issues, a new compression method is proposed, leveraging a deep autoencoder for the first time to significantly improve the compression ratio. Additionally, the method reduces error by compressing and transmitting residual data from the feature extraction process using quantization coding and Huffman coding. Furthermore, a mean filter based on the optimal standard deviation threshold is applied to further minimize error. Experimental results show that the proposed method achieves an average compression ratio of 4.05 for inclination and azimuth data; compared to the DPCM method, it is improved by 118.54%. Meanwhile, the average mean square error of the proposed method is 76.88, which is decreased by 82.46% when compared to the DPCM method. Ablation studies confirm the effectiveness of the proposed improvements. These findings highlight the efficacy of the proposed method in enhancing wellbore stability monitoring performance. [ABSTRACT FROM AUTHOR]

Current assessments for generalized anxiety disorder (GAD) are often subjective and do not rely on a standardized measure to evaluate the GAD across its severity levels. The lack of objective and multi-level quantitative diagnostic criteria poses as a significant challenge for individualized treatment strategies. To address this need, this study aims to establish a GAD grading and quantification diagnostic model by integrating an electroencephalogram (EEG) and ensemble learning. In this context, a total of 39 normal subjects and 80 GAD patients were recruited and divided into four groups: normal control, mild GAD, moderate GAD, and severe GAD. Ten minutes resting state EEG data were collected for every subject. Functional connectivity features were extracted from each EEG segment with different time windows. Then, ensemble learning was employed for GAD classification studies and brain mechanism analysis. Hence, the results showed that the Catboost model with a 10 s time window achieved an impressive 98.1% accuracy for four-level classification. Particularly, it was found that those functional connections situated between the frontal and temporal lobes were significantly more abundant than in other regions, with the beta rhythm being the most prominent. The analysis framework and findings of this study provide substantial evidence for the applications of artificial intelligence in the clinical diagnosis of GAD. [ABSTRACT FROM AUTHOR]

Pine wilt disease (PWD) is a forest disease characterized by rapid spread and extremely high lethality, posing a serious threat to the ecological security of China's forests and causing significant economic losses in forestry. Given the extensive forestry area, limited personnel for inspection and monitoring, and high costs, utilizing UAV-based remote sensing monitoring for diseased trees represents an effective approach for controlling the spread of PWD. However, due to the small target size and uneven scale of pine wilt disease, as well as the limitations of real-time detection by drones, traditional disease tree detection algorithms based on RGB remote sensing images do not achieve an optimal balance among accuracy, detection speed, and model complexity due to real-time detection limitations. Consequently, this paper proposes Light-ViTeYOLO, a lightweight pine wilt disease detection method based on Vision Transformer-enhanced YOLO (You Only Look Once). A novel lightweight multi-scale attention module is introduced to construct an EfficientViT feature extraction network for global receptive field and multi-scale learning. A novel neck network, CACSNet(Content-Aware Cross-Scale bidirectional fusion neck network), is designed to enhance the detection of diseased trees at single granularity, and the loss function is optimized to improve localization accuracy. The algorithm effectively reduces the number of parameters and giga floating-point operations per second (GFLOPs) of the detection model while enhancing overall detection performance. Experimental results demonstrate that compared with other baseline algorithms, Light-ViTeYOLO proposed in this paper has the least parameter and computational complexity among related algorithms, with 3.89 MFLOPs and 7.4 GFLOPs, respectively. The FPS rate is 57.9 (frames/s), which is better than the original YOLOv5. Meanwhile, its mAP@0.5:0.95 is the best among the baseline algorithms, and the recall and mAP@0.5 slightly decrease. Our Light-ViTeYOLO is the first lightweight method specifically designed for detecting pine wilt disease. It not only meets the requirements for real-time detection of pine wilt disease outbreaks but also provides strong technical support for automated forestry work. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) need to replicate feature detectors when modeling spatial information, which reduces their efficiency. The number of replicated feature detectors or labeled training data required for such methods grows exponentially with the dimensionality of the data being used. On the other hand, space-insensitive methods are difficult to encode and express effectively due to the limitation of their rich text structures. In response to the above problems, this paper proposes a capsule network (self-attention capsule network, or SA-CapsNet) with a self-attention mechanism for text classification tasks, wherein the capsule network itself, given the feature with the symmetry hint on two ends, acts as both encoder and decoder. In order to learn long-distance dependent features in sentences and encode text information more efficiently, SA-CapsNet maps the self-attention module to the feature extraction layer of the capsule network, thereby increasing its feature extraction ability and overcoming the limitations of convolutional neural networks. In addition, in this study, in order to improve the accuracy of the model, the capsule was improved by reducing its dimension and an intermediate layer was added, enabling the model to obtain more expressive instantiation features in a given sentence. Finally, experiments were carried out on three general datasets of different sizes, namely the IMDB, MPQA, and MR datasets. The accuracy of the model on these three datasets was 84.72%, 80.31%, and 75.38%, respectively. Furthermore, compared with the benchmark algorithm, the model's performance on these datasets was promising, with an increase in accuracy of 1.08%, 0.39%, and 1.43%, respectively. This study focused on reducing the parameters of the model for various applications, such as edge and mobile applications. The experimental results show that the accuracy is still not apparently decreased by the reduced parameters. The experimental results therefore verify the effective performance of the proposed SA-CapsNet model. [ABSTRACT FROM AUTHOR]

Crowd anomaly detection is crucial in enhancing surveillance and crowd management. This paper proposes an efficient approach that combines spatial and temporal visual descriptors, sparse feature tracking, and neural networks for efficient crowd anomaly detection. The proposed approach utilises diverse local feature extraction methods, including SIFT, FAST, and AKAZE, with a sparse feature tracking technique to ensure accurate and consistent tracking. Delaunay triangulation is employed to represent the spatial distribution of features in an efficient way. Visual descriptors are categorised into individual behaviour descriptors and interactive descriptors to capture the temporal and spatial characteristics of crowd dynamics and behaviour, respectively. Neural networks are then utilised to classify these descriptors and pinpoint anomalies, making use of their strong learning capabilities. A significant component of our study is the assessment of how dimensionality reduction methods, particularly autoencoders and PCA, affect the feature set's performance. This assessment aims to balance computational efficiency and detection accuracy. Tests conducted on benchmark crowd datasets highlight the effectiveness of our method in identifying anomalies. Our approach offers a nuanced understanding of crowd movement and patterns by emphasising both individual and collective characteristics. The visual and local descriptors facilitate high-level analysis by closely relating to semantic information and crowd behaviour. The analysis observed shows that this approach offers an efficient framework for crowd anomaly detection, contributing to improved crowd management and public safety. The proposed model achieves accuracy of 99.5 %, 96.1%, 99.0% and 88.5% in the UMN scenes 1, 2, and 3 and violence in crowds datasets, respectively. [ABSTRACT FROM AUTHOR]

Foreign objects on power transmission lines carry a significant risk of triggering large-scale power interruptions which may have serious consequences for daily life if they are not detected and handled in time. To accurately detect foreign objects on power transmission lines, this paper proposes a TL-Yolo method based on the Yolov8 framework. Firstly, we design a full-dimensional dynamic convolution (ODConv) module as a backbone network to enhance the feature extraction capability, thus retaining richer semantic content and important visual features. Secondly, we present a feature fusion framework combining a weighted bidirectional feature pyramid network (BiFPN) and multiscale attention (MSA) module to mitigate the degradation effect of multiscale feature representation in the fusion process, and efficiently capture the high-level feature information and the core visual elements. Thirdly, we utilize a lightweight GSConv cross-stage partial network (GSCSP) to facilitate efficient cross-level feature fusion, significantly reducing the complexity and computation of the model. Finally, we employ the adaptive training sample selection (ATSS) strategy to balance the positive and negative samples, and dynamically adjust the selection process of the training samples according to the current state and performance of the model, thus effectively reducing the object misdetection and omission. The experimental results show that the average detection accuracy of the TL-Yolo method reaches 91.30%, which is 4.20% higher than that of the Yolov8 method. Meanwhile, the precision and recall metrics of our method are 4.64% and 3.53% higher than those of Yolov8. The visualization results also show the superior detection performance of the TL-Yolo algorithm in real scenes. Compared with the state-of-the-art methods, our method achieves higher accuracy and speed in the detection of foreign objects on power transmission lines. [ABSTRACT FROM AUTHOR]

In the field of intelligent connected vehicles, the precise and real-time identification of speed bumps is critically important for the safety of autonomous driving. To address the issue that existing visual perception algorithms struggle to simultaneously maintain identification accuracy and real-time performance amidst image distortion and complex environmental conditions, this study proposes an enhanced lightweight neural network framework, YOLOv5-FPNet. This framework strengthens perception capabilities in two key phases: feature extraction and loss constraint. Firstly, FPNet, based on FasterNet and Dynamic Snake Convolution, is developed to adaptively extract structural features of distorted speed bumps with accuracy. Subsequently, the C3-SFC module is proposed to augment the adaptability of the neck and head components to distorted features. Furthermore, the SimAM attention mechanism is embedded within the backbone to enhance the ability of key feature extraction. Finally, an adaptive loss function, Inner–WiseIoU, based on a dynamic non-monotonic focusing mechanism, is designed to improve the generalization and fitting ability of bounding boxes. Experimental evaluations on a custom speed bumps dataset demonstrate the superior performance of FPNet, with significant improvements in key metrics such as the mAP, mAP50_95, and FPS by 38.76%, 143.15%, and 51.23%, respectively, compared to conventional lightweight neural networks. Ablation studies confirm the effectiveness of the proposed improvements. This research provides a fast and accurate speed bump detection solution for autonomous vehicles, offering theoretical insights for obstacle recognition in intelligent vehicle systems. [ABSTRACT FROM AUTHOR]

Analyzing point clouds with neural networks is a current research hotspot. In order to analyze the 3D geometric features of point clouds, most neural networks improve the network performance by adding local geometric operators and trainable parameters. However, deep learning usually requires a large amount of computational resources for training and inference, which poses challenges to hardware devices and energy consumption. Therefore, some researches have started to try to use a nonparametric approach to extract features. Point-NN combines nonparametric modules to build a nonparametric network for 3D point cloud analysis, and the nonparametric components include operations such as trigonometric embedding, farthest point sampling (FPS), k-nearest neighbor (k-NN), and pooling. However, Point-NN has some blindness in feature embedding using the trigonometric function during feature extraction. To eliminate this blindness as much as possible, we utilize a nonparametric energy function-based attention mechanism (ResSimAM). The embedded features are enhanced by calculating the energy of the features by the energy function, and then the ResSimAM is used to enhance the weights of the embedded features by the energy to enhance the features without adding any parameters to the original network; Point-NN needs to compute the similarity between each feature at the naive feature similarity matching stage; however, the magnitude difference of the features in vector space during the feature extraction stage may affect the final matching result. We use the Squash operation to squeeze the features. This nonlinear operation can make the features squeeze to a certain range without changing the original direction in the vector space, thus eliminating the effect of feature magnitude, and we can ultimately better complete the naive feature matching in the vector space. We inserted these modules into the network and build a nonparametric network, Point-Sim, which performs well in 3D classification tasks. Based on this, we extend the lightweight neural network Point-SimP by adding some trainable parameters for the point cloud classification task, which requires only 0.8 M parameters for high performance analysis. Experimental results demonstrate the effectiveness of our proposed algorithm in the point cloud shape classification task. The corresponding results on ModelNet40 and ScanObjectNN are 83.9% and 66.3% for 0 M parameters—without any training—and 93.3% and 86.6% for 0.8 M parameters. The Point-SimP reaches a test speed of 962 samples per second on the ModelNet40 dataset. The experimental results show that our proposed method effectively improves the performance on point cloud classification networks. [ABSTRACT FROM AUTHOR]

The unique imaging modality of synthetic aperture radar (SAR) has posed significant challenges for object detection, making it more complex to acquire and interpret than optical images. Recently, numerous studies have proposed cross-domain adaptive methods based on convolutional neural networks (CNNs) to promote SAR object detection using optical data. However, existing cross-domain methods focus on image features, lack improvement on input data, and ignore the valuable supervision provided by few labeled SAR images. Therefore, we propose a semi-supervised cross-domain object detection framework that uses optical data and few SAR data to achieve knowledge transfer for SAR object detection. Our method focuses on the data processing aspects to gradually reduce the domain shift at the image, instance, and feature levels. First, we propose a data augmentation method of image mixing and instance swapping to generate a mixed domain that is more similar to the SAR domain. This method fully utilizes few SAR annotation information to reduce domain shift at image and instance levels. Second, at the feature level, we propose an adaptive optimization strategy to filter out mixed domain samples that significantly deviate from the SAR feature distribution to train feature extractor. In addition, we employ Vision Transformer (ViT) as feature extractor to handle the global feature extraction of mixed images. We propose a detection head based on normalized Wasserstein distance (NWD) to enhance objects with smaller effective regions in SAR images. The effectiveness of our proposed method is evaluated on public SAR ship and oil tank datasets. [ABSTRACT FROM AUTHOR]

Acquiring disparity maps by dense stereo matching is one of the most important methods for producing digital surface models. However, the characteristics of optical satellite imagery, including significant occlusions and long baselines, increase the challenges of dense matching. In this study, we propose an end-to-end edge-guided multi-scale matching network (EGMS-Net) tailored for optical satellite stereo image pairs. Using small convolutional filters and residual blocks, the EGMS-Net captures rich high-frequency signals during the initial feature extraction phase. Subsequently, pyramid features are derived through efficient down-sampling and consolidated into cost volumes. To regularize these cost volumes, we design a top–down multi-scale fusion network that integrates an attention mechanism. Finally, we innovate the use of trainable guided filter layers in disparity refinement to improve edge detail recovery. The network is trained and evaluated using the Urban Semantic 3D and WHU-Stereo datasets, with subsequent analysis of the disparity maps. The results show that the EGMS-Net provides superior results, achieving endpoint errors of 1.515 and 2.459 pixels, respectively. In challenging scenarios, particularly in regions with textureless surfaces and dense buildings, our network consistently delivers satisfactory matching performance. In addition, EGMS-Net reduces training time and increases network efficiency, improving overall results. [ABSTRACT FROM AUTHOR]

Land use/cover change (LUCC) refers to the phenomenon of changes in the Earth's surface over time. Accurate prediction of LUCC is crucial for guiding policy formulation and resource management, contributing to the sustainable use of land, and maintaining the health of the Earth's ecosystems. LUCC is a dynamic geographical process involving complex spatiotemporal dependencies. Existing LUCC simulation models suffer from insufficient spatiotemporal feature learning, and traditional cellular automaton (CA) models exhibit limitations in neighborhood effects. This study proposes a cellular automaton model based on spatiotemporal feature learning and hotspot area pre-allocation (VST-PCA). The model utilizes the video swin transformer to acquire transformation rules, enabling a more accurate capture of the spatiotemporal dependencies inherent in LUCC. Simultaneously, a pre-allocation strategy is introduced in the CA simulation to address the local constraints of neighborhood effects, thereby enhancing the simulation accuracy. Using the Chongqing metropolitan area as the study area, two traditional CA models and two deep learning-based CA models were constructed to validate the performance of the VST-PCA model. Results indicated that the proposed VST-PCA model achieved Kappa and FOM values of 0.8654 and 0.4534, respectively. Compared to other models, Kappa increased by 0.0322–0.1036, and FOM increased by 0.0513–0.1649. This study provides an accurate and effective method for LUCC simulation, offering valuable insights for future research and land management planning. [ABSTRACT FROM AUTHOR]

Domain Name System (DNS) plays an infrastructure role in providing the directory service for mapping domains to IPs on the Internet. Considering the foundation and openness of DNS, it is not surprising that adversaries register massive domains to enable multiple malicious activities, such as spam, command and control (C&C), malware distribution, click fraud, etc. Therefore, detecting malicious domains is a significant topic in security research. Although a substantial quantity of research has been conducted, previous work has failed to fuse multiple relationship features to uncover the deep underlying relationships between domains, thus largely limiting their level of performance. In this paper, we proposed AGCN-Domain to detect malicious domains by combining various relations. The core concept behind our work is to analyze relations between domains according to their behaviors in multiple perspectives and fuse them intelligently. The AGCN-Domain model utilizes three relationships (client relation, resolution relation, and cname relation) to construct three relationship feature graphs to extract features and intelligently fuse the features extracted from the graphs through an attention mechanism. After the relationship features are extracted from the domain names, they are put into the trained classifier to be processed. Through our experiments, we have demonstrated the performance of our proposed AGCN-Domain model. With 10% initialized labels in the dataset, our AGCN-Domain model achieved an accuracy of 94.27% and the F1 score of 87.93%, significantly outperforming other methods in the comparative experiments. [ABSTRACT FROM AUTHOR]

A bearing fault is one of the major causes of rotating machinery faults. However, in real industrial scenarios, the harsh and complex environment makes it very difficult to collect sufficient fault data. Due to this limitation, most of the current methods cannot accurately identify the fault type in cases with limited data, so timely maintenance cannot be conducted. In order to solve this problem, a bearing fault diagnosis method based on the fractional order Siamese deep residual shrinkage network (FO-SDRSN) is proposed in this paper. After data collection, all kinds of vibration data are first converted into two-dimensional time series feature maps, and these feature maps are divided into the same or different types of fault sample pairs. Then, a Siamese network based on the deep residual shrinkage network (DRSN) is used to extract the features of the fault sample pairs, and the fault type is determined according to the features. After that, the contrastive loss function and diagnostic loss function of the sample pairs are combined, and the network parameters are continuously optimized using the fractional order momentum gradient descent method to reduce the loss function. This improves the accuracy of fault diagnosis with a small sample training dataset. Finally, four small sample datasets are used to verify the effectiveness of the proposed method. The results show that the FO-SDRSN method is superior to other advanced methods in terms of training accuracy and stability under small sample conditions. [ABSTRACT FROM AUTHOR]

Ferromagnetic debris in lubricating oil, serving as an important communication carrier, can effectively reflect the wear condition of mechanical equipment and predict the remaining useful life. In practice application, the detection signals collected by using inductive sensors contain not only debris signals but also noise terms, and weak debris features are prone to be distorted, which makes it a severe challenge to debris signature identification and quantitative estimation. In this paper, a debris signature extraction method established on segmentation entropy with an adaptive threshold was proposed, based on which five identification indicators were investigated to improve detection accuracy. The results of the simulations and oil experiment show that the proposed algorithm can effectively identify wear particles and preserve debris signatures. [ABSTRACT FROM AUTHOR]

Synchronous analysis is one of the most effective and practical techniques in rotating machinery diagnostics, especially in cases with variable speed operations. A modern analog-to-digital convertor (ADC) usually digitizes an analog signal to an equal time interval data series. Synchronous resampling converts the data series from an equal time interval data series to an equal shaft rotation angle interval data series. This conversion is usually achieved in the digital domain with the aid of shaft speed information, through either direct measurement or identification from a measured vibration signal, which is a time-consuming process. In order to improve the computational efficiency as well as the data processing accuracy, in this paper, a fast synchronous time-point calculation method based on an inverse function interpolation procedure is proposed. By identifying the inverse function of the instantaneous phase with respect to time, the calculation process of synchronous time points is optimized, which results in improved calculation efficiency and accuracy. These advantages are demonstrated by numerical simulations as well as experimental verifications. The numerical simulation results show that the proposed method can improve calculation speed by about five times. The synchronous analysis based on the proposed method was applied to a bearing fault detection in a high-speed rail carriage, which demonstrated the advantages of the proposed algorithm in improving the signal-to-noise ratio (SNR) for bearing damage feature extraction. [ABSTRACT FROM AUTHOR]

Crop lodging is an important cause of direct economic losses and secondary disease transmission in agricultural production. Most existing methods for segmenting wheat lodging areas use a large-volume network, which poses great difficulties for annotation and crop monitoring in real time. Therefore, an ultra-lightweight model, Lodging-U2NetP (L-U2NetP), based on a novel annotation strategy which crops the images before annotating them (Crop-annotation), was proposed and applied to RGB images of wheat captured with an unmanned aerial vehicle (UAV) at a height of 30 m during the maturity stage. In the L-U2NetP, the Dual Cross-Attention (DCA) module was firstly introduced into each small U-structure effectively to address semantic gaps. Then, Crisscross Attention (CCA) was used to replace several bulky modules for a stronger feature extraction ability. Finally, the model was compared with several classic networks. The results showed that the L-U2NetP yielded an accuracy, F1 score, and IoU (Intersection over Union) for segmenting of 95.45%, 93.11%, 89.15% and 89.72%, 79.95%, 70.24% on the simple and difficult sub-sets of the dataset (CA set) obtained using the Crop-annotation strategy, respectively. Additionally, the L-U2NetP also demonstrated strong robustness in the real-time detection simulations and the dataset (AC set) obtained using the mainstream annotation strategy, which annotates images before cropping (Annotation-crop). The results indicated that L-U2NetP could effectively extract wheat lodging and the Crop-annotation strategy provided a reliable performance which is comparable with that of the mainstream one. [ABSTRACT FROM AUTHOR]

Infrared and visible light image fusion combines infrared and visible light images by extracting the main information from each image and fusing it together to provide a more comprehensive image with more features from the two photos. Infrared and visible image fusion has gained popularity in recent years and is increasingly being employed in sectors such as target recognition and tracking, night vision, scene segmentation, and others. In order to provide a concise overview of infrared and visible picture fusion, this paper first explores its historical context before outlining current domestic and international research efforts. Then, conventional approaches for infrared and visible picture fusion, such as the multi-scale decomposition method and the sparse representation method, are thoroughly introduced. The advancement of deep learning in recent years has greatly aided the field of picture fusion. The outcomes of the fusion have a wide range of potential applications due to the neural networks' strong feature extraction and reconstruction skills. As a result, this research also evaluates deep learning techniques. After that, some common objective evaluation indexes are provided, and the performance evaluation of infrared and visible image fusion is introduced. The common datasets in the areas of infrared and visible image fusion are also sorted out at the same time. Datasets play a significant role in the advancement of infrared and visible image fusion and are an essential component of infrared and visible image fusion testing. The application of infrared and visible image fusion in many domains is then simply studied with practical examples, particularly in developing fields, used to show its application. Finally, the prospect of the current infrared and visible image fusion field is presented, and the full text is summarized. [ABSTRACT FROM AUTHOR]

Scene-matching navigation is one of the essential technologies for achieving precise navigation in satellite-denied environments. Selecting suitable-matching areas is crucial for planning trajectory and reducing yaw. Most traditional selection methods of suitable-matching areas use hierarchical screening based on multiple feature indicators. However, these methods rarely consider the interrelationship between different feature indicators and use the same set of screening thresholds for different categories of images, which has poor versatility and can easily cause mis-selection and omission. To solve this problem, a suitable-matching areas' selection method based on multi-level saliency is proposed. The matching performance score is obtained by fusing several segmentation levels' salient feature extraction results and performing weighted calculations with the sub-image edge density. Compared with the hierarchical screening methods, the matching performance of the candidate areas selected by our algorithm is at least 22.2% higher, and it also has a better matching ability in different scene categories. In addition, the number of missed and wrong selections is significantly reduced. The average matching accuracy of the top three areas selected by our method reached 0.8549, 0.7993, and 0.7803, respectively, under the verification of multiple matching algorithms. Experimental results show this paper's suitable-matching areas' selection method is more robust. [ABSTRACT FROM AUTHOR]

Accurate litchi identification is of great significance for orchard yield estimations. Litchi in natural scenes have large differences in scale and are occluded by leaves, reducing the accuracy of litchi detection models. Adopting traditional horizontal bounding boxes will introduce a large amount of background and overlap with adjacent frames, resulting in a reduced litchi detection accuracy. Therefore, this study innovatively introduces the use of the rotation detection box model to explore its capabilities in scenarios with occlusion and small targets. First, a dataset on litchi rotation detection in natural scenes is constructed. Secondly, three improvement modules based on YOLOv8n are proposed: a transformer module is introduced after the C2f module of the eighth layer of the backbone network, an ECA attention module is added to the neck network to improve the feature extraction of the backbone network, and a 160 × 160 scale detection head is introduced to enhance small target detection. The test results show that, compared to the traditional YOLOv8n model, the proposed model improves the precision rate, the recall rate, and the mAP by 11.7%, 5.4%, and 7.3%, respectively. In addition, four state-of-the-art mainstream detection backbone networks, namely, MobileNetv3-small, MobileNetv3-large, ShuffleNetv2, and GhostNet, are studied for comparison with the performance of the proposed model. The model proposed in this article exhibits a better performance on the litchi dataset, with the precision, recall, and mAP reaching 84.6%, 68.6%, and 79.4%, respectively. This research can provide a reference for litchi yield estimations in complex orchard environments. [ABSTRACT FROM AUTHOR]

Facial beauty prediction (FBP) is a leading research subject in the field of artificial intelligence (AI), in which computers make facial beauty judgments and predictions similar to those of humans. At present, the methods are mainly based on deep neural networks. However, there still exist some problems such as insufficient label information and overfitting. Multi-task learning uses label information from multiple databases, which increases the utilization of label information and enhances the feature extraction ability of the network. Attentional feature fusion (AFF) combines semantic information and introduces an attention mechanism to reduce the risk of overfitting. In this study, the multi-task learning of an adaptive sharing policy combined with AFF is presented based on the adaptive sharing (AdaShare) network in FBP. First, an adaptive sharing policy is added to multi-task learning with ResNet18 as the backbone network. Second, the AFF is introduced at the short skip connections of the network. The proposed method improves the accuracy of FBP by solving the problems of insufficient label information and overfitting issues. The experimental results based on the large-scale Asia facial beauty database (LSAFBD) and SCUT-FBP5500 databases show that the proposed method outperforms the single-database single-task baseline and can be applied extensively in image classification and other fields. [ABSTRACT FROM AUTHOR]

Effective vehicle detection plays a crucial role in various applications in cities, including traffic management, urban planning, vehicle transport, and surveillance systems. However, existing vehicle detection methods suffer from low recognition accuracy, high computational costs, and excessive parameters. To address these challenges, this paper proposed a high-precision and lightweight detector along with a new dataset for construction-related vehicles. The dataset comprises 8425 images across 13 different categories of vehicles. The detector was based on a modified version of the You Only Look Once (YOLOv4) algorithm. DenseNet was utilized as the backbone to optimize feature transmission and reuse, thereby improving detection accuracy and reducing computational costs. Additionally, the detector employed depth-wise separable convolutions to optimize the model structure, specifically focusing on the lightweight neck and head components. Furthermore, H-swish was used to enhance non-linear feature extraction. The experimental results demonstrated that the proposed detector achieves a mean average precision (mAP) of 96.95% on the provided dataset, signifying a 4.03% improvement over the original YOLOv4. The computational cost and parameter count of the detector were 26.09GFLops and 16.08 MB, respectively. The proposed detector not only achieves lower computational costs but also provides higher detection when compared to YOLOv4 and other state-of-the-art detectors. [ABSTRACT FROM AUTHOR]

Images captured from different viewpoints or devices have often exhibited significant geometric and photometric differences due to factors such as environmental variations, camera technology differences, and shooting conditions' instability. To address this problem, homography estimation has attracted much attention as a method to describe the geometric projection relationship between images. Researchers have proposed numerous homography estimation methods for single-source and multimodal images in the past decades. However, the comprehensive review and analysis of homography estimation methods, from feature-based to deep learning-based, is still lacking. Therefore, we provide a comprehensive overview of research advances in homography estimation methods. First, we provide a detailed introduction to homography estimation's core principles and matrix representations. Then, we review homography estimation methods for single-source and multimodal images, from feature-based to deep learning-based methods. Specifically, we analyze traditional and learning-based methods for feature-based homography estimation methods in detail. For deep learning-based homography estimation methods, we explore supervised, unsupervised, and other methods in-depth. Subsequently, we specifically review several metrics used to evaluate these methods. After that, we analyze the relevant applications of homography estimation and show the broad application prospects of this technique. Finally, we discuss current challenges and future research directions, providing a reference for computer vision researchers and engineers. [ABSTRACT FROM AUTHOR]

When working with objects on a smaller scale, higher detection accuracy and faster detection speed are desirable features. Researchers aim to endow drones with these attributes in order to improve performance when patrolling in controlled areas for object detection. In this paper, we propose an improved YOLOv7 model. By incorporating the variability attention module into the backbone network of the original model, the association between distant pixels is increased, resulting in more effective feature extraction and, thus, improved model detection accuracy. By improving the original network model with deformable convolution modules and depthwise separable convolution modules, the model enhances the semantic information extraction of small objects and reduces the number of model parameters to a certain extent. Pretraining and fine-tuning techniques are used for training, and the model is retrained on the VisDrone2019 dataset. Using the VisDrone2019 dataset, the improved model achieves an mAP50 of 52.3% on the validation set. Through the visual comparative analysis of the detection results in our validation set, we find that the model shows a significant improvement in detecting small objects compared with previous iterations. [ABSTRACT FROM AUTHOR]

Reliability and robustness are fundamental requisites for the successful integration of deep-learning models into real-world applications. Deployed models must exhibit an awareness of their limitations, necessitating the ability to discern out-of-distribution (OOD) data and prompt human intervention, a critical competency. While several frameworks for OOD detection have been introduced and achieved remarkable results, most state-of-the-art (SOTA) models rely on supervised learning with annotated data for their training. However, acquiring labeled data can be a demanding, time-consuming or, in some cases, an infeasible task. Consequently, unsupervised learning has gained substantial traction and has made noteworthy advancements. It empowers models to undergo training solely on unlabeled data while still achieving comparable or even superior performance compared to supervised alternatives. Among the array of unsupervised methods, contrastive learning has asserted its effectiveness in feature extraction for a variety of downstream tasks. Conversely, auto-encoders are extensively employed to acquire indispensable representations that faithfully reconstruct input data. In this study, we introduce a novel approach that amalgamates contrastive learning with auto-encoders for OOD detection using unlabeled data. Contrastive learning diligently tightens the grouping of in-distribution data while meticulously segregating OOD data, and the auto-encoder augments the feature space with increased refinement. Within this framework, data undergo implicit classification into in-distribution and OOD categories with a notable degree of precision. Our experimental findings manifest that this method surpasses most of the existing detectors reliant on unlabeled data or even labeled data. By incorporating an auto-encoder into an unsupervised learning framework and training it on the CIFAR-100 dataset, our model enhances the detection rate of unsupervised learning methods by an average of 5.8 % . Moreover, it outperforms the supervised-based OOD detector by an average margin of 11 % . [ABSTRACT FROM AUTHOR]

Image denoising, as an essential component of image pre-processing, effectively reduces noise interference to enhance image quality, a factor of considerable research importance. Traditional denoising methods often lead to the blurring of image details and a lack of realism at the image edges. To deal with these issues, we propose an image denoising algorithm named Residual structure and Cooperative Attention mechanism based on Generative Adversarial Networks (RCA-GAN). This algorithm proficiently reduces noise while focusing on preserving image texture details. To maximize feature extraction, this model first employs residual learning within a portion of the generator's backbone, conducting extensive multi-dimensional feature extraction to preserve a greater amount of image details. Secondly, it introduces a simple yet efficient cooperative attention module to enhance the representation capacity of edge and texture features, further enhancing the preservation of intricate image details. Finally, this paper constructs a novel loss function—the Multimodal Loss Function—for the network training process. The experimental results were evaluated using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) as evaluation metrics. The experimental results demonstrate that the proposed RCA-GAN image denoising algorithm has increased the average PSNR from 24.71 dB to 33.76 dB, achieving a 36.6% improvement. Additionally, the average SSIM value has risen from 0.8451 to 0.9503, indicating a 12.4% enhancement. It achieves superior visual outcomes, showcasing the ability to preserve image texture details to a greater extent and excel in edge preservation and noise suppression. [ABSTRACT FROM AUTHOR]

The method of acoustic radiation signal detection not only enables contactless measurement but also provides comprehensive state information during equipment operation. This paper proposes an enhanced feature extraction network (EFEN) for fault diagnosis of rolling bearings based on acoustic signal feature learning. The EFEN network comprises four main components: the data preprocessing module, the information feature selection module (IFSM), the channel attention mechanism module (CAMM), and the convolutional neural network module (CNNM). Firstly, the one-dimensional acoustic signal is transformed into a two-dimensional grayscale image. Then, IFSM utilizes three different-sized convolution filters to process input image data and fuse and assign weights to feature information that can attenuate noise while highlighting effective fault information. Next, a channel attention mechanism module is introduced to assign weights to each channel. Finally, the convolutional neural network (CNN) fault diagnosis module is employed for accurate classification of rolling bearing faults. Experimental results demonstrate that the EFEN network achieves high accuracy in fault diagnosis and effectively detects rolling bearing faults based on acoustic signals. The proposed method achieves an accuracy of 98.52%, surpassing other methods in terms of performance. In comparative analysis of antinoise experiments, the average accuracy remains remarkably high at 96.62%, accompanied by a significantly reduced average iteration time of only 0.25 s. Furthermore, comparative analysis confirms that the proposed algorithm exhibits excellent accuracy and resistance against noise. [ABSTRACT FROM AUTHOR]

The utilization of multiscale entropy methods to characterize vibration signals has proven to be promising in intelligent diagnosis of mechanical equipment. However, in the current multiscale entropy methods, only the information in the low-frequency range is utilized and the information in the high-frequency range is discarded. In order to take full advantage of the information, in this paper, a fault feature extraction method utilizing the bidirectional composite coarse-graining process with fuzzy dispersion entropy is proposed. To avoid the redundancy of the full frequency range feature information, the Random Forest algorithm combined with the Maximum Relevance Minimum Redundancy algorithm is applied to feature selection. Together with the K-nearest neighbor classifier, a rolling bearing intelligent diagnosis framework is constructed. The effectiveness of the proposed framework is evaluated by a numerical simulation and two experimental examples. The validation results demonstrate that the extracted features by the proposed method are highly sensitive to the bearing health conditions compared with hierarchical fuzzy dispersion entropy, composite multiscale fuzzy dispersion entropy, multiscale fuzzy dispersion entropy, multiscale dispersion entropy, multiscale permutation entropy, and multiscale sample entropy. In addition, the proposed method is able to identify the fault categories and health states of rolling bearings simultaneously. The proposed damage detection methodology provides a new and better framework for intelligent fault diagnosis of rolling bearings in rotating machinery. [ABSTRACT FROM AUTHOR]

The objective of vehicle search is to locate and identify vehicles in uncropped, real-world images, which is the combination of two tasks: vehicle detection and re-identification (Re-ID). As an emerging research topic, vehicle search plays a significant role in the perception of cooperative autonomous vehicles and road driving in the distant future and has become a trend in the future development of intelligent driving. However, there is no suitable dataset for this study. The Tsinghua University DAIR-V2X dataset is utilized to create the first cross-camera vehicle search dataset, DAIR-V2XSearch, which combines the cameras at both ends of the vehicle and the road in real-world scenes. The primary purpose of the current search network is to address the pedestrian issue. Due to varying task scenarios, it is necessary to re-establish the network in order to resolve the problem of vast differences in different perspectives caused by vehicle searches. A phased feature extraction network (PFE-Net) is proposed as a solution to the cross-camera vehicle search problem. Initially, the anchor-free YOLOX framework is selected as the backbone network, which not only improves the network's performance but also eliminates the fuzzy situation in which multiple anchor boxes correspond to a single vehicle ID in the Re-ID branch. Second, for the vehicle Re-ID branch, a camera grouping module is proposed to effectively address issues such as sudden changes in perspective and disparities in shooting under different cameras. Finally, a cross-level feature fusion module is designed to enhance the model's ability to extract subtle vehicle features and the Re-ID's precision. Experiments demonstrate that our proposed PFE-Net achieves the highest precision in the DAIR-V2XSearch dataset. [ABSTRACT FROM AUTHOR]

The extraction of sandy roads from remote sensing images is important for field ecological patrols and path planning. Extraction studies on sandy roads face limitations because of various factors (e.g., sandy roads may have poor continuity, may be obscured by external objects, and/or have multi-scale and banding characteristics), in addition to the absence of publicly available datasets. Accordingly, in this study, we propose using the remote sensing imagery of a sandy road (RSISR) dataset and design a sandy road extraction model (Parallel Attention Mechanism-Unet, or PAM-Unet) based on Gaofen-2 (GF-2) satellite images. Firstly, the model uses a residual stacking module, which can solve the problem of poor road feature consistency and improve the extraction of fine features. Secondly, we propose a parallel attention module (PAM), which can reduce the occlusion effect of foreign objects on roads during the extraction process and improve feature map reduction. Finally, with this model, the SASPP (Strip Atrous Spatial Pyramid Pooling) structure, which enhances the model's ability to perceive contextual information and capture banding features, is introduced at the end of the encoder. For this study, we conducted experiments on road extraction using the RSISR dataset and the DeepGlobe dataset. The final results show the following: (a) On the RSISR dataset, PAM-Unet achieves an IoU value of 0.762, and its F1 and IoU values are improved by 2.7% and 4.1%, respectively, compared to U-Net. In addition, compared to the models Unet++ and DeepLabv3+, PAM-Unet improves IoU metrics by 3.6% and 5.3%, respectively. (b) On the DeepGlobe dataset, the IoU value of PAM-Unet is 0.658; compared with the original U-Net, the F1 and IoU values are improved by 2.5% and 3.1%, respectively. The experimental results show that PAM-Unet has a positive impact by way of improving the continuity of sandy road extraction and reducing the occlusion of irrelevant features, and it is an accurate, reliable, and effective road extraction method. [ABSTRACT FROM AUTHOR]

Determining the types of light curves has been a challenge due to the massive amount of light curves generated by large sky survey programs. In the literature, the light curves classification methods are overly dependent on the imaging quality of the light curves, so the classification results are often poor. In this paper, a new method is proposed to classify the Kepler light curves from Quarter 1, and consists of two parts: feature extraction and classification neural network construction. In the first part, features are extracted from the light curves using three different methods, and then the features are fused (transform domain features, light curve flux statistics features, and Kepler photometry features). In the second part, a classification neural network RLNet, based on Residual Network (ResNet) and Long Short Term Memory (LSTM), is proposed. The experiment involved the classification of approximately 150,000 Kepler light curves into 11 categories. The results show that this new method outperforms seven other methods in all metrics, with an accuracy of 0.987, a minimum recall of 0.968, and a minimum precision of 0.970 under all categories. [ABSTRACT FROM AUTHOR]

This study researched the application of a convolutional neural network (CNN) to a bearing compound fault diagnosis. The proposed idea lies in the ability of CNN to automatically extract fault features from complex raw signals. In our approach, to extract more effective features from a raw signal, a novel deep convolutional neural network combining global feature extraction with detailed feature extraction (GDDCNN) is proposed. First, wide and small kernel sizes are separately adopted in shallow and deep convolutional layers to extract global and detailed features. Then, the modified activation layer with a concatenated rectified linear unit (CReLU) is added following the shallow convolution layer to improve the utilization of shallow global features of the network. Finally, to acquire more robust features, another strategy involving the GMP layer is utilized, which replaces the traditional fully connected layer. The performance of the obtained diagnosis was validated on two bearing datasets. The results show that the accuracy of the compound fault diagnosis is over 98%. Compared with three other CNN-based methods, the proposed model demonstrates better stability. [ABSTRACT FROM AUTHOR]

Quasars have an important role in the studies of galaxy evolution and star formation. The rare close projection of two quasars in the sky allows us to study the environment and matter exchange around the foreground quasar ( Q S O f g ) and the background quasar ( Q S O b g ). This paper proposes a pipeline DPQP for quasar pair (QP) candidates' detection based on photometric images and the corresponding spectra. The pipeline consists of three main parts: a target source detector, a regressor, and a discriminator. In the first part, the target source detection network–YOLOv4 (TSD-YOLOv4) and the target source classification network (TSCNet) are used in sequence to detect quasars in SDSS photometric images. In the second part, a depth feature extraction network of quasar images (DE-QNet) is constructed to estimate the redshifts of quasars from photometric images. In the third part, a quasar pair score (Q-Score) metric is proposed based on the spectral analysis. The larger the Q-Score, the greater the possibility of two pairs being a quasar pair. The experimental results show that between redshift 1.0 and 4.0, the MAE of DE-QNet is 0.316, which is 16.1% lower than the existing method. Samples with | Δ z| < 0.15 account for 77.1% of the test dataset. A new table with 1025 QP candidates is provided by traversing 50,000 SDSS photometric images. [ABSTRACT FROM AUTHOR]

Accurate location information has significant commercial and economic value as they are widely used in intelligent manufacturing, material localization and smart homes. Magnetic sequence-based approaches show great promise mainly due to their pervasiveness and stability. However, existing geomagnetic indoor localization methods are facing the problems of location ambiguity and feature extraction deficiency, which will lead to large localization errors. To address these issues, we propose a coarse-to-fine geomagnetic indoor localization method based on deep learning. First, a multidimensional geomagnetic feature extraction method is presented which can extract magnetic features from spatial and temporal aspects. Then, a hierarchical deep neural network model is devised to extract more accurate geomagnetic information and corresponding location clues for more accurate localization. Finally, localization is achieved through a particle filter combined with IMU localization. To evaluate the performance of the proposed methods, we carried out several experiments at three trial paths with two heterogeneous devices, Vivo X30 and Huawei Mate30. Experimental results demonstrate that the proposed algorithm can achieve more accurate localization performance than the state-of-the-art methods. Meanwhile, the proposed algorithm has low cost and good pervasiveness for different devices. [ABSTRACT FROM AUTHOR]

The electrocardiogram (ECG) is a crucial tool for assessing cardiac health in humans. Aiming to enhance the accuracy of ECG signal classification, a novel approach is proposed based on relative position matrix and deep learning network information features for the classification task in this paper. The approach improves the feature extraction capability and classification accuracy via techniques of image conversion and attention mechanism. In terms of the recognition strategy, this paper presents an image conversion using relative position matrix information. This information is utilized to describe the relative spatial relationships between different waveforms, and the image identification is successfully applied to the Gam-Resnet18 deep learning network model with a transfer learning concept for classification. Ultimately, this model achieved a total accuracy of 99.30%, an average positive prediction rate of 98.76%, a sensitivity of 98.90%, and a specificity of 99.84% with the relative position matrix approach. To evaluate the effectiveness of the proposed method, different image conversion techniques are compared on the test set. The experimental results demonstrate that the relative position matrix information can better reflect the differences between various types of arrhythmias, thereby improving the accuracy and stability of classification. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) images have special physical scattering characteristics owing to their unique imaging mechanism. Traditional deep learning algorithms usually extract features from real-valued SAR images in a purely data-driven manner, which may ignore some important physical scattering characteristics and sacrifice some useful target information in SAR images. This undoubtedly limits the improvement in performance for SAR target recognition. To take full advantage of the physical information contained in SAR images, a complex-valued network guided with sub-aperture decomposition (CGS-Net) for SAR target recognition is proposed. According to the fact that different targets have different physical scattering characteristics at different angles, the sub-aperture decomposition is used to improve accuracy with a multi-task learning strategy. Specifically, the proposed method includes main and auxiliary tasks, which can improve the performance of the main task by learning and sharing useful information from the auxiliary task. Here, the main task is the target recognition task, and the auxiliary task is the target reconstruction task. In addition, a complex-valued network is used to extract the features from the original complex-valued SAR images, which effectively utilizes the amplitude and phase information in SAR images. The experimental results obtained using the MSTAR dataset illustrate that the proposed CGS-Net achieved an accuracy of 99.59% (without transfer learning or data augmentation) for the ten-classes targets, which is superior to the other popular deep learning methods. Moreover, the proposed method has a lightweight network structure, which is suitable for SAR target recognition tasks because SAR images usually lack a large number of labeled data. Here, the experimental results obtained using the small dataset further demonstrate the excellent performance of the proposed CGS-Net. [ABSTRACT FROM AUTHOR]

The precise localization of unmanned ground vehicles (UGVs) in industrial parks without prior GPS measurements presents a significant challenge. Simultaneous localization and mapping (SLAM) techniques can address this challenge by capturing environmental features, using sensors for real-time UGV localization. In order to increase the real-time localization accuracy and efficiency of UGVs, and to improve the robustness of UGVs' odometry within industrial parks—thereby addressing issues related to UGVs' motion control discontinuity and odometry drift—this paper proposes a tightly coupled LiDAR-IMU odometry method based on FAST-LIO2, integrating ground constraints and a novel feature extraction method. Additionally, a novel maintenance method of prior maps is proposed. The front-end module acquires the prior pose of the UGV by combining the detection and correction of relocation with point cloud registration. Then, the proposed maintenance method of prior maps is used to hierarchically and partitionally segregate and perform the real-time maintenance of the prior maps. At the back-end, real-time localization is achieved by the proposed tightly coupled LiDAR-IMU odometry that incorporates ground constraints. Furthermore, a feature extraction method based on the bidirectional-projection plane slope difference filter is proposed, enabling efficient and accurate point cloud feature extraction for edge, planar and ground points. Finally, the proposed method is evaluated, using self-collected datasets from industrial parks and the KITTI dataset. Our experimental results demonstrate that, compared to FAST-LIO2 and FAST-LIO2 with the curvature feature extraction method, the proposed method improved the odometry accuracy by 30.19% and 48.24% on the KITTI dataset. The efficiency of odometry was improved by 56.72% and 40.06%. When leveraging prior maps, the UGV achieved centimeter-level localization accuracy. The localization accuracy of the proposed method was improved by 46.367% compared to FAST-LIO2 on self-collected datasets, and the located efficiency was improved by 32.33%. The z-axis-located accuracy of the proposed method reached millimeter-level accuracy. The proposed prior map maintenance method reduced RAM usage by 64% compared to traditional methods. [ABSTRACT FROM AUTHOR]

Image inpainting is an active area of research in image processing that focuses on reconstructing damaged or missing parts of an image. The advent of deep learning has greatly advanced the field of image restoration in recent years. While there are many existing methods that can produce high-quality restoration results, they often struggle when dealing with images that have large missing areas, resulting in blurry and artifact-filled outcomes. This is primarily because of the presence of invalid information in the inpainting region, which interferes with the inpainting process. To tackle this challenge, the paper proposes a novel approach called separable mask update convolution. This technique automatically learns and updates the mask, which represents the missing area, to better control the influence of invalid information within the mask area on the restoration results. Furthermore, this convolution method reduces the number of network parameters and the size of the model. The paper also introduces a regional normalization technique that collaborates with separable mask update convolution layers for improved feature extraction, thereby enhancing the quality of the restored image. Experimental results demonstrate that the proposed method performs well in restoring images with large missing areas and outperforms state-of-the-art image inpainting methods significantly in terms of image quality. [ABSTRACT FROM AUTHOR]

For very-high-resolution (VHR) remote sensing images with complex objects and rich textural information, multi-difference image fusion has been proven as an effective method to improve the performance of change detection. However, errors are superimposed during this process and a single spectral feature cannot fully utilize the correlation between pixels, resulting in low robustness. To overcome these problems and optimize the performance of multi-difference image fusion in change detection, we propose a novel multi-difference image fusion change detection method based on a visual attention model (VA-MDCD). First, we construct difference images using change vector analysis (CVA) and spectral gradient difference (SGD). Second, we use the visual attention model to calculate multiple color, intensity and orientation features of the difference images to obtain the difference saliency images. Third, we use the wavelet transform fusion algorithm to fuse two saliency images. Finally, we execute the OTSU threshold segmentation algorithm (OTSU) to obtain the final change detection map. To validate the effectiveness of VA-MDCD on VHR images, two datasets of Jilin 1 and Beijing 2 are selected for experiments. Compared with classical methods, the proposed method has a better performance with fewer missed alarms (MA) and false alarms (FA), which proves that the method has a strong robustness and generalization ability. The F-measure of the two datasets is 0.6671 and 0.7313, respectively. In addition, the results of ablation experiments confirm that the three feature extraction modules of the model all play a positive role. [ABSTRACT FROM AUTHOR]

Dynamic objects bring about a large number of error accumulations in pose estimation of mobile robots in dynamic scenes, and result in the failure to build a map that is consistent with the surrounding environment. Along these lines, this paper presents a robust semi-direct 3D simultaneous localization and mapping (SLAM) algorithm for mobile robots based on dense optical flow. First, a preliminary estimation of the robot's pose is conducted using the sparse direct method and the homography matrix is utilized to compensate for the current frame image to reduce the image deformation caused by rotation during the robot's motion. Then, by calculating the dense optical flow field of two adjacent frames and segmenting the dynamic region in the scene based on the dynamic threshold, the local map points projected within the dynamic regions are eliminated. On this basis, the robot's pose is optimized by minimizing the reprojection error. Moreover, a high-performance keyframe selection strategy is developed, and keyframes are inserted when the robot's pose is successfully tracked. Meanwhile, feature points are extracted and matched to the keyframes for subsequent optimization and mapping. Considering that the direct method is subject to tracking failure in practical application scenarios, the feature points and map points of keyframes are employed in robot relocation. Finally, all keyframes and map points are used as optimization variables for global bundle adjustment (BA) optimization, so as to construct a globally consistent 3D dense octree map. A series of simulations and experiments demonstrate the superior performance of the proposed algorithm. [ABSTRACT FROM AUTHOR]