Search

Aiming at the problems of low detection accuracy, high computational complexity and long‐time consumption of visual perception model in a complex mining environment, this research designs a visual information perception system of coal mine comprehensive excavation working face for an edge computing terminal. Firstly, the C3‐Fast feature extraction module, spatial pyramid pooling with cross‐stage partial connection (SPPCSPC) pooling module, bi‐directional feature pyramid network and lightweight decoupled detection head are used to optimize the YOLOv5s model, so as to construct the FSBD‐YOLOv5s multi‐object detection model. Secondly, the pruning and distillation algorithm is used to lighten the FSBD‐YOLOv5s model, and the model complexity is greatly reduced while maintaining the model detection accuracy. Further, the lightweight FSBD‐YOLOv5s model is migrated and deployed to the edge computing terminal platform and the TensorRT engine is used to accelerate model inference. Finally, experiments are carried out based on the data set of the coal mine comprehensive excavation working face. The experimental results show that on the edge computing terminal platform, the parameters and computational volume of the lightweight FSBD‐YOLOv5s model are reduced by 50.8% and 34.0%, while its detection accuracy and speed reach 94.0% and 43.7 fps, which can fully satisfy the requirements of the accuracy and real‐time for the coal mine engineering applications. [ABSTRACT FROM AUTHOR]

Detecting small targets in infrared images is crucial for ground surveillance and air traffic control. However, distinguishing small infrared targets from similar backgrounds is challenging due to their lack of structural and textural characteristics. To address these challenges, this study proposes a novel global information‐aware network with global interaction graph attention (GIGA) for infrared small target detection. The GIGA consists of a global interaction layer (GILayer), graph attention weights (GAW), and a global relational learning (GRL) module. Specifically, the GILayer dynamically learns global inter‐pixel relationships of small target images by enhancing the dependencies between feature dimensions. The GAW component calculates pixel‐by‐pixel similarity across the entire feature map using graph attention mechanisms, while the GRL module retains critical similarity features in the feature extraction network, thereby facilitating small target detection. Additionally, the multi‐scale context fusion module utilises self‐attention and dilation convolution to complement richer feature details at different scales. Experimental results on both natural and synthetic datasets demonstrate the proposed method's superiority over other state‐of‐the‐art conventional and deep learning approaches in infrared small target detection. [ABSTRACT FROM AUTHOR]

Accurately identifying tropical fish serves as a crucial indicator, offering an insight into the state of marine biodiversity and the condition of coral reef ecosystems. However, the current detection networks are prone to omission and misidentification due to occlusion between fish and the complex underwater environment. This paper proposes a modified approach named FishFocusNet, in which alterable kernel convolution modules, asymptotic feature pyramid network (AFPN), and Shape‐IoU are integrated into YOLOv8. To extract a more comprehensive set of fish features, AKConv modules with arbitrary kernel sizes are proposed to take the place of the conventional fixed‐shaped kernels in the backbone for downsampling. AFPN is adopted as the feature integration structure in the neck, which enhances feature fusion and adaptive spatial fusion between non‐adjacent layers. In the detector head, Shape‐IoU is employed to achieve precise localization of fish targets. The superiorities of these modifications are proved by ablation experiments and comparative experiments. The experimental results show that the optimized approach obtained an mAP of 81.8% accompanied by 2.4 MB parameters and 3.6 GB FLOPS. Meanwhile, compared with more complicated models of similar scale, the proposed method can enhance recognition accuracy to 84.2% and significantly reduce computational costs. [ABSTRACT FROM AUTHOR]

Presently, State Space Models (SSMs), including frameworks like Mamba, have been incorporated into the realm of computer vision. These models not only sustain remote interactions and encapsulate global semantic information effectively, but also preserve linear computational complexity, offering a balance between performance and computational efficiency. Given that Mamba inherently adheres to the principle of selectivity when constructing sequence models, the goal is to further unleash the potential of Mamba through this innovative combination of convolution and self‐attention, improve accuracy and minimize the number of parameters while achieving linear complexity. Mamba is employed as an encoder to distill semantic information from the image, and it is supplemented with convolutional blocks, thereby conserving the details of the image. Concurrently, embedding prompts at a deeper level enhances its adaptability to cater to diverse requirements. Lastly, a bidirectional attention mechanism is incorporated for inference, striving to retain both global connections and local details to the maximum extent. This culminates in a novel, lightweight medical segmentation model. Exhaustive experiments were executed on six public datasets. The empirical results show that the proposed model exhibits competitive performance in medical image segmentation tasks. [ABSTRACT FROM AUTHOR]

Edge devices are increasingly utilized for defect detection in power line inspection, necessitating algorithms that optimize model size and accuracy. This study introduces a lightweight detection method using the Optimized Feature Network with MobileOne‐FPN‐NASHead (OFN network) OFN network and distillation technique. The OFN incorporates a lightweight backbone, neural network search, re‐parametrization, and a feature pyramid to create a compact yet effective detection network. To enhance feature learning, a heterogeneous distillation approach is applied, leveraging a modified YOLOv8 as a teacher network. This modification includes an explicit visual centre for improved global and local information extraction, crucial for dense target detection in power line inspections. Additionally, the Minimize the points distance IoU (MPDloU) loss function is used to improve localization accuracy over the the Complete‐Intersection Over Union (CIoU) loss. Experimental results show a 1.1% mean Average Precision (mAP) increase for the enhanced YOLOv8 and a 70.2% mAP for the OFN network with 18.95 GFLOPs and 343 FPS, achieving a commendable balance between model efficiency and detection performance. The research underscores the viability of the OFN for edge computing in power line defect detection, highlighting the potential of innovative algorithmic structures in this application. [ABSTRACT FROM AUTHOR]

Cardiac hemangioma is a rare benign tumour that presents diagnostic challenges due to its variable clinical symptoms, imaging features, and locations. This study proposes a novel segmentation method based on a Convolutional Neural Network (CNN) and Transformer integration, with Swin‐UNet as the core model. We incorporated a U‐shaped convolutional neural network block into the original jump connection of Swin‐UNet. The Binary Cross Entropy Loss (BCE Loss) algorithm was added, and the learning rate decay algorithm was modified to select the appropriate one by comparing loss values. This paper utilizes the publicly available cardiac angioma dataset in AI Studio, consisting of 215 images for training and testing. To evaluate the effectiveness of the proposed model, this paper demonstrates its optimality through ablation experiments and comparisons with other mainstream models. The comparison experiments show that this model improves Dice by approximately 12%, HD95 by approximately 4.7 mm, Accuracy by approximately 6.1%, and F1 score by 0.11 compared to models such as UNet, UNet++, and Deeplabv3+, etc. For the recently proposed SOTO models, such as TransUNet, Swin‐UNet, and MultiResUnet, the Dice score improved by about 1.2%, HD95 reduced by about 1mm, Accuracy improved by about 0.3%, and F1 score improved by 0.015. [ABSTRACT FROM AUTHOR]

The complex nature of human brain tissues is important in ensuring accurate diagnosis to save human lives. Research on early detection of brain diseases has gained significant prominence within medical intelligence using highly complex model architectures with only a single label that cannot be verified. This paper introduces an innovative approach to Siamese Network Genetic Algorithm (SN‐GA) leveraging Siamese contrastive learning for classifying brain images across diverse diseases. Our core architecture is a Bi‐Convolutional Neural Network (Bi‐CNN) optimized by a genetic algorithm to enhance brain image classification. Specifically, five widely recognized transfer learning‐based architectures, namely AlexNet, Efficient‐B0, VGG‐16, ResNet‐50, and Inception‐v3, have been incorporated to evaluate the effectiveness of the proposed SN‐GA system. The performance of these models has been rigorously analyzed and compared using two distinct datasets: Brain tumors and Alzheimer's datasets. The experimental results robustly affirm the efficacy of the proposed Siamese model, yielding exceptional levels of accuracy, precision, and recall, all peaking at 97%. These findings underscore the potential and resilience of the optimized Siamese network in the context of brain disease classification, emphasizing its significance in advancing the field of medical imaging and diagnosis, with implications for early intervention and patient care. [ABSTRACT FROM AUTHOR]

Image denoising aims to restore a clean image from a noisy image. Traditional methods utilizing convolutional neural networks (CNN) for denoising are trained using pairs of noisy and clean images to comprehend the transformation from a noisy image to a clean one. However, the acquisition of such image pairs in real‐world scenarios presents a challenge. Hence, numerous self‐supervised denoising techniques have been developed that do not require clean images for training. This study demonstrates that a straightforward loss design, concentrating on variance, can effectively train a standard CNN denoiser in a self‐supervised fashion. A novel theoretical framework is introduced for training a basic CNN denoising model using three constraints: mean, variance, and augmentation. The variance constraint is crucial as it prevents the trained model from converging to trivial solutions such as identity or zero mapping. This theory provides valuable insights for the development of new self‐supervised denoising methods. Furthermore, a method that applies this theory to proposed dual networks is developed, which consist of two standard CNN models predicting both the clean image and the noise. This approach enhances model capacity during training while minimizing computational costs during inference. This method exemplifies the implementation of the variance constraint and introduces a data constraint for dual networks. Notably, the proposed method only assumes the presence of additive white noise, irrespective of the noise distribution. This minimal assumption enhances the model's robustness against noise with complex or unknown distributions in real‐world distorted images. Experimental results indicate that the proposed Noise2Variance method exhibits commendable performance on peak signal noise ratio and structural similarity metrics compared to existing self‐supervised denoising techniques. Visual comparison of results further substantiates the efficacy of the proposed method. A comparison of model complexity reveals that the method is efficient among the compared CNN‐based techniques. [ABSTRACT FROM AUTHOR]

The high‐precision visual perception results are easily affected by the lens flare issue when the image sensor is facing to strong light. The existing flare removal methods have poor robustness when confronted with flare interference caused by complex nighttime lighting, which has to preserve natural light source information. A simulated dataset for the removal of night flares is created to solve the problem of collecting complete paired training data, and night flare removal network (NFR‐Net) is proposed to remove the interference caused by various light disturbances at night. The light source extraction module is introduced to retain light source information realistically and effectively in night vision scenes. Extensive experimental results demonstrate that the proposed method is superior to the existing related methods in the various complex night vision scenes. The proposed NFR‐Net can enhance visual perception of nighttime images significantly and improve the performance of night vision tasks. [ABSTRACT FROM AUTHOR]

Semantic segmentation of underwater fish images is vital for monitoring fish stocks, assessing marine resources, and sustaining fisheries. To tackle challenges such as low segmentation accuracy, inadequate real‐time performance, and imprecise location segmentation in current methods, a novel lightweight U‐Net model is proposed. The proposed model acquires more segmentation details by applying a multiple‐input approach at the first four encoder levels. To achieve both lightweight and high accuracy, a multi‐scale residual structure (MRS) module is proposed to reduce parameters and compensate for the accuracy loss caused by the reduction of channels. To improve segmentation accuracy, a multi‐scale skip connection (MSC) structure is further proposed, and the convolution block attention mechanism (CBAM) is introduced at the end of each decoder level for weight adjustment. Experimental results demonstrate a notable reduction in model volume, parameters, and floating‐point operations by 94.20%, 94.39%, and 51.52% respectively, compared to the original model. The proposed model achieves a high mean intersection over union (mIOU) of 94.44%, mean pixel accuracy (mPA) of 97.03%, and a frame rate of 43.62 frames per second (FPS). With its high precision and minimal parameters, the model strikes a balance between accuracy and speed, making it particularly suitable for underwater image segmentation. [ABSTRACT FROM AUTHOR]

The problem of human identification through recognition of patterns in iris images captured in unconstrained environments results in image artefacts such as image occlusion and specular reflection, in which iris tissue is observable to extremely low content. To overcome this problem, this paper presents a novel method for iris image retrieval and recognition based on partial pattern matching. The main contribution of the proposed method relies on an image partitioning schema in which the iris is divided into non‐overlapping blocks with varying dimensions, facilitating the identification and removal of image regions impaired by eyelids, eyelashes, and specular reflections. In fact, the blocks that contain artefacts are completely ignored and those blocks are preserved that include useful patterns for identification. In addition, a multi‐feature similarity followed by a score fusion technique is employed for ranking the retrieval results. The remarkable results of the classification stage include an accuracy of 100%, 98.75%, and 99.94% on three benchmark databases, including UPOL, UBIRIS.V2, and CASIA‐Iris‐Interval.v3, respectively. Additionally, in the retrieval stage, the proposed method achieves a precision of 100% on all three benchmark databases, a recall of 83.33%, and a F1‐measure of 90.91 on the CASIA‐Iris‐Interval.v3 dataset. [ABSTRACT FROM AUTHOR]

The detection of defects on the copper chain in the production process of tobacco cutters is crucial for ensuring product quality. Traditional defect detection methods often rely on spatial domain image analysis, which not only has a large computational load but also performs poorly in handling high‐frequency noise and complex backgrounds. To address this issue, this paper proposes a novel neural network model based on frequency domain analysis, called frequency domain attention network. This network first utilizes discrete cosine transform to transform the image from the spatial domain to the frequency domain, effectively reducing computational complexity and improving processing speed. Subsequently, through the innovative frequency domain attention module, the network automatically identifies and enhances key discriminative features in the frequency domain, thereby strengthening the model's ability to identify defects. Finally, the frequency domain attention map, after feature extraction and integration, is inputted into the coupling detection head to achieve high‐precision defect detection. The experimental results show that our method outperforms the SOTA method with an increase of 0.03 in AP and 21 in FPS. [ABSTRACT FROM AUTHOR]

How to extract age‐independent identity features from face images has long been the major challenge in cross‐age face recognition task. In this letter, a class‐wised domain decoupling‐guided adversarial feature learning network to extract age‐independent face features is proposed. In this model, an adversarial feature learning module is designed to decompose identity features and age features. Considering that artificially designed age interference suppression strategies are difficult to fit the complex relationship between identity features and age features, an adversarial training strategy incorporated with an attention mechanism in the adversarial feature learning module is introduced to suppress age interference adaptively. Besides, under the idea of maximizing the distribution difference of identity feature domain and age feature domain, a class‐wised domain decoupling module is further designed to guide the model to extract age‐independent identity features. The proposed model has been validated on the well‐known public datasets CALFW and CACD‐VS, where it achieved remarkable recognition accuracy rates of 94.5% and 99.5%, respectively. This represents improvements of 4.2% and 0.1% over the state‐of‐the‐art single‐task‐based models, clearly showcasing the effectiveness of the proposed class‐wised domain decoupling‐guided adversarial feature learning model. [ABSTRACT FROM AUTHOR]

Aiming at the problems of slow speed and poor accuracy of traditional millimeter wave sparse imaging, a sparse imaging algorithm based on graph convolution model is proposed from the perspective of sparse signal recovery. The graph signal model is constructed by combining the low‐rank and piecewise smoothing(LRPS) regular terms, based on which the proximal operator is replaced by the denoising graph convolution network, and the graph convolution sparse reconstruction network LRPS‐GCN is constructed, and the recovered target image is obtained by iterating with the optimal non‐linear sparse variation. For the proposed algorithm, simulation experiments are carried out using synthetic datasets under different target densities, iteration times and noise environments, and compared with the traditional graph signal reconstruction algorithm and the deep compressed sensing reconstruction algorithm, and then use the measured data with varying degrees of sparsity to validate. The experimental results show that the reconstructed images by this algorithm have better performance in terms of normalised mean square error, target to background ratio, reconstruction time and memory usage. [ABSTRACT FROM AUTHOR]

Leveraging the advanced functionalities of modern radio frequency (RF) modeling and simulation tools, specifically designed for adaptive radar processing applications, this paper presents a data‐driven approach to improve accuracy in radar target localization post adaptive radar detection. To this end, we generate a large number of radar returns by randomly placing targets of variable strengths in a predefined area, using RFView®, a high‐fidelity, site‐specific, RF modeling & simulation tool. We produce heatmap tensors from the radar returns, in range, azimuth [and Doppler], of the normalized adaptive matched filter (NAMF) test statistic. We then train a regression convolutional neural network (CNN) to estimate target locations from these heatmap tensors, and we compare the target localization accuracy of this approach with that of peak‐finding and local search methods. This empirical study shows that our regression CNN achieves a considerable improvement in target location estimation accuracy. The regression CNN offers significant gains and reasonable accuracy even at signal‐to‐clutter‐plus‐noise ratio (SCNR) regimes that are close to the breakdown threshold SCNR of the NAMF. We also study the robustness of our trained CNN to mismatches in the radar data, where the CNN is tested on heatmap tensors collected from areas that it was not trained on. We show that our CNN can be made robust to mismatches in the radar data through few‐shot learning, using a relatively small number of new training samples. [ABSTRACT FROM AUTHOR]

Due to the richness of natural image semantics, natural image colourisation is a challenging problem. Existing methods often suffer from semantic confusion due to insufficient semantic understanding, resulting in unreasonable colour assignments, especially at the edges of objects. This phenomenon is referred to as colour bleeding. The authors have found that using the self‐attention mechanism benefits the model's understanding and recognition of object semantics. However, this leads to another problem in colourisation, namely dull colour. With this in mind, a Position‐Spatial Attention Network(PSANet) is proposed to address the colour bleeding and the dull colour. Firstly, a novel new attention module called position‐spatial attention module (PSAM) is introduced. Through the proposed PSAM module, the model enhances the semantic understanding of images while solving the dull colour problem caused by self‐attention. Then, in order to further prevent colour bleeding on object boundaries, a gradient‐aware loss is proposed. Lastly, the colour bleeding phenomenon is further improved by the combined effect of gradient‐aware loss and edge‐aware loss. Experimental results show that this method can reduce colour bleeding largely while maintaining good perceptual quality. [ABSTRACT FROM AUTHOR]

Deep learning‐based face recognition models have demonstrated remarkable performance in benchmark tests, and knowledge distillation technology has been frequently accustomed to obtain high‐precision real‐time face recognition models specifically designed for mobile and embedded devices. However, in recent years, the knowledge distillation methods for face recognition, which mainly focus on feature or logit knowledge distillation techniques, neglect the attention mechanism that play an important role in the domain of neural networks. An innovation cross‐stage connection review path of the attention cosine similarity knowledge distillation method that unites the attention mechanism with review knowledge distillation method is proposed. This method transfers the attention map obtained from the teacher network to the student through a cross‐stage connection path. The efficacy and excellence of the proposed algorithm are demonstrated in popular benchmark tests. [ABSTRACT FROM AUTHOR]

With the development of automatic driving and path planning technology, predicting the moving trajectory of pedestrians in dynamic scenes has become one of key and urgent technical problems. However, most of the existing techniques regard all pedestrians in the scene as equally important influence on the predicted pedestrian's trajectory, and the existing methods which use sequence‐based time‐series generative models to obtain the predicted trajectories, do not allow for parallel computation, it will introduce a significant computational overhead. A new social trajectory prediction network, Social‐ATPGNN which integrates both temporal information and spatial one based on ATPGNN is proposed. In space domain, the pedestrians in the predicted scene are formed into an undirected and non fully connected graph, which solves the problem of homogenisation of pedestrian relationships, then, the spatial interaction between pedestrians is encoded to improve the accuracy of modelling pedestrian social consciousness. After acquiring high‐level spatial data, the method uses Temporal Convolutional Network which could perform parallel calculations to capture the correlation of time series of pedestrian trajectories. Through a large number of experiments, the proposed model shows the superiority over the latest models on various pedestrian trajectory datasets. [ABSTRACT FROM AUTHOR]

Bird‐related outages greatly threaten the safety of overhead transmission and distribution lines, while electrocution and collisions of birds with power lines, especially endangered species, are significant environmental concerns. Automatic bird recognition can be helpful to mitigate this contradiction. This paper proposes a method for automatic classification of bird species related to power line faults combining deep convolution features with error‐correcting output codes support vector machine (ECOC‐SVM). An image dataset of about 20 high‐risk and 20 low‐risk bird species was constructed, and the feed‐forward denoising convolutional neural network was used for image preprocessing. The deep convolution features of bird images were extracted by DarkNet‐53, and taken as inputs of the ECOC‐SVM for model training and bird species classification. The gradient‐weighted class activation mapping was used for visual explanations of the model decision region. The experimental results indicate that the average accuracy of the proposed method can reach 94.39%, and its performance was better than other models using different feature extraction networks and classification algorithms. [ABSTRACT FROM AUTHOR]

It is difficult to identify an arc fault accurately when the loads on the user side are more complicated, which hinders the development of low‐voltage monitoring and pre‐warning inspection. This study acquired a series of arc‐fault signals according to IEC 62606. The main time‐frequency features were strengthened with high efficiency by applying the generalized S‐transform to them with a bi‐Gaussian window. Further, the power spectrum density determination allowed for the detection of imperceptible high‐frequency harmonic energy reflections, thus increasing the rate of arc‐fault diagnosis and making it suitable for arc‐fault monitoring of non‐linear loads. The final samples were trained and classified using a 2D convolutional neural network and the overall accuracy of identification was observed to be 98.13%, which involved various domestic loads, thus providing a reference for follow‐up arc‐fault monitoring and inspection research. [ABSTRACT FROM AUTHOR]

Driving while inattentive or fatigued significantly contributes to traffic accidents and puts road users at a significantly higher risk of collision. The rise in road accidents due to driver inattention resulting from distractive objects, for example, mobile phones, drinking, or tiredness, requires intelligent traffic monitoring systems to promote road safety. However, outdated detection technologies cannot handle the poor accuracy and the lack of real‐time processing possibility especially when combined with the variations of driving environment. This paper introduces "ME‐YOLOv8" which operates driver's distraction and fatigue through a modified version of YOLOv8, which includes modules multi‐head self‐attention (MHSA) and efficient channel attention (ECA) modules applied, where the goal of MHSA is to improve the sensitivity of global features and the ECA attentions focus on critical features. Additionally, a dataset was created containing 3660 images covering multiple distracted and drowsy driver scenarios. The results reflect the enhanced detection capabilities of ME‐YOLOv8 and demonstrate its effectiveness in real‐time scenarios. This study demonstrates a significant advancement in the application of AI to public safety and highlights the critical role that state‐of‐the‐art deep learning algorithms play in lowering the risks associated with distracted and tired driving. [ABSTRACT FROM AUTHOR]

Predicting traffic flow is vital for optimizing transportation efficiency, reducing fuel consumption, and minimizing commute times. While artificial intelligence tools have been effective in addressing this, there have been some difficulties in processing spatial and temporal data. Current transformer‐based methods, although cutting‐edge for traffic prediction, encounter challenges with handling long sequences and capturing temporal relations effectively. Addressing these, the research introduces a model combining multi‐scale attention modules within transformer layers. This model employs spatio‐temporal transformer blocks, enriched with multi‐scale convolutional attention mechanisms, allowing for a deeper understanding of temporal and spatial traffic patterns. This unique attention mechanism enhances data feature interpretation, leading to heightened prediction precision. The tests on extensive traffic datasets showcase the model's prowess in capturing both local and global traffic features, resulting in superior traffic status predictions. In summary, the innovative model offers an efficacious approach to long‐sequence traffic data learning and temporal relationship extraction, setting a new benchmark in traffic flow prediction accuracy. [ABSTRACT FROM AUTHOR]

Ship classification is an important technique for enhancing maritime management and security. Visible and infrared sensors are generally employed to deal with the challenging problem and improve classification performance. Herein, a two‐branch feature fusion neural network structure is proposed to classify the visible and infrared maritime vessel images simultaneously. Specifically, in this two‐branch neural network, one branch is based on a deep convolutional neural network that is used to extract the visible image features, while the other is a hybrid network structure that is a multi‐scale patch embedding network called MPANet. The sub‐network MPANet can extract fine‐ and coarse‐grained features, in which the pooling operation instead of the multi‐head attention mechanism is utilized to reduce memory consumption. When there are infrared images, it is used to extract the infrared image features, otherwise, this branch is also utilized to extract visible image features. Therefore, this dual network is suitable with or without infrared images. The experimental results on the visible and infrared spectrums (VAIS) dataset demonstrate that the introduced network achieves state‐of‐the‐art ship classification performance on visible images and paired visible and infrared ship images. [ABSTRACT FROM AUTHOR]

Transformer possesses a broader perceptual scope, while the Convolutional Neural Network (CNN) excels at capturing local information. In this paper, the authors propose the Multi‐Sclale Feature Aggregation Network (MSFA‐Net) for single‐image dehazing which is fused with the advantages of Transformer and CNN. Our MSFA‐Net is based on the encoder–decoder structure, and there are four main innovations. Firstly, the authors make some improvements to the original Swin Transformer to make it more effective for dehazing tasks, and the authors name it Spatial Information Aggregation Transformer (SIAT). The authors place the SIAT in both encoder and decoder of MSFA‐Net for feature extraction. The authors propose an upsampling module called Efficient Spatial Resolution Recovery (ESRR) which is placed in the decoder part. Compared to commonly used transposed convolutions, the authors' ESRR module has fewer computational cost. Considering that the haze distribution is always uneven and the information from each channel is different, the authors introduce the Dynamic Multi‐Attention (DMA) module to provide pixel‐wise weights and channel‐wise weights for input features. The authors place the DMA module between the encoder and decoder parts. As the network depth increases, the spatial structural information from the high‐resolution layer tends to degrade. To deal with the problem, the authors propose the Multi‐Scale Feature Fusion (MSFF) module to recover missing spatial structural information. The authors place the MSFF module in both the encoder and decoder parts. Extensive experimental results show that the authors' proposed dehazing network achieves state‐of‐the‐art dehazing performance with relatively low computational cost. [ABSTRACT FROM AUTHOR]

Traffic sign detection is critical for autonomous driving technology. However, accurately detecting traffic signs in complex traffic environments remains challenge despite the widespread use of one‐stage detection algorithms known for their real‐time processing capabilities. In this paper, the authors propose a traffic sign detection method based on YOLO v8. Specifically, this study introduces the Space‐to‐Depth (SPD) module to address missed detections caused by multi‐scale variations of traffic signs in traffic scenes. The SPD module compresses spatial information into depth channels, expanding the receptive field and enhancing the detection capabilities for objects of varying sizes. Furthermore, to address missed detections caused by complex backgrounds such as trees, this paper employs the Select Kernel attention mechanism. This mechanism enables the model to dynamically adjust its focus and more effectively concentrate on key features. Additionally, considering the uneven distribution of training data, the authors adopted the WIoUv3 loss function, which optimizes loss calculation through a weighted approach, thereby improving the model's detection performance across various sizes and frequencies of instances. The proposed methods were validated on the CCTSDB and TT100K datasets. Experimental results demonstrate that the authors' method achieves substantial improvements of 3.2% and 5.1% on the mAP50 metric compared to YOLOv8s, while maintaining high detection speed, significantly enhancing the overall performance of the detection system. The code for this paper is located at https://github.com/dusongjie/TSD‐YOLO‐Small‐Traffic‐Sign‐Detection‐Based‐on‐Improved‐YOLO‐v8 [ABSTRACT FROM AUTHOR]

In recent years, deep learning methods were good solutions for object detection in synthetic aperture radar (SAR) images. However, the problems of complex scenarios, large object scale differences and imperfect fine‐grained classification in ship detection were intractable. In response, an improved model GDB‐YOLOv5s (Improved YOLOv5s model incorporating global attention mechanism (GAM), DCN‐v2 and BiFusion) is designed. This model introduces deformable convolution networks (DCN‐v2) into the Backbone to enhance the adaptability of the receptive field. It replaces the original Neck's PANet structure with a BiFusion structure to better fuse the extracted multiscale features. Additionally, it integrates GAM into the network to reduce information loss and improve global feature interaction. Experiments were conducted on single‐class dataset SSDD and multi‐class dataset SRSSD‐V1.0. The results show that the GDB‐YOLOv5s model improves mean average precision scores (mAP) significantly, outperforming the original YOLOv5s model and other traditional methods. GDB‐YOLOv5s also improves Precision‐score (P) and Recall‐score (R) for fine‐grained classification to some extent, thereby reducing false alarms and missed detections. It has been proved that the improved model is relatively effective. [ABSTRACT FROM AUTHOR]

Visual defect recognition techniques based on deep learning models are crucial for modern industrial quality inspection. The backbone, serving as the primary feature extraction component of the defect recognition model, has not been thoroughly exploited. High‐performance vision transformer (ViT) is less adopted due to high computational complexity and limitations of computational resources and storage hardware in industrial scenarios. This paper presents LSA‐Former, a lightweight transformer architectural backbone that integrates the benefits of convolution and ViT. LSA‐Former proposes a novel self‐attention with linear computational complexity, enabling it to capture local and global semantic features with fewer parameters. LSA‐Former is pre‐trained on ImageNet‐1K and surpasses state‐of‐the‐art methods. LSA‐Former is employed as the backbone for various detectors, evaluated specifically on the PCB defect detection task. The proposed method reduces at least 18M parameters and exceeds the baseline by more than 2.2 mAP. [ABSTRACT FROM AUTHOR]

Tomographic synthetic aperture radar is an advanced multi‐channel interferometric technique for retrieving 3‐D spatial information. It can be regarded as an inherently sparse reconstruction problem and can be solved using compressive sensing algorithms. However, the performances are limited by the number of acquisitions and suffer from computational burdens in practice. This paper proposes a novel method based on deep learning, which is carried out and optimized in an end‐to‐end manner by the generative adversarial neural networks. The proposed method applies the cascaded U‐Net architectures to achieve the reconstruction of full‐channel synthetic aperture radar images and the refinement of obtained tomographic results, respectively. The proposed network is trained using simulated data and validate the technique on simulated and real data. The tests show promising results with the limited number of acquisitions while reducing the computation time. [ABSTRACT FROM AUTHOR]

Abstract Aiming at the problems of slow speed and poor accuracy of traditional millimeter wave sparse imaging, a sparse imaging algorithm based on graph convolution model is proposed from the perspective of sparse signal recovery. The graph signal model is constructed by combining the low‐rank and piecewise smoothing(LRPS) regular terms, based on which the proximal operator is replaced by the denoising graph convolution network, and the graph convolution sparse reconstruction network LRPS‐GCN is constructed, and the recovered target image is obtained by iterating with the optimal non‐linear sparse variation. For the proposed algorithm, simulation experiments are carried out using synthetic datasets under different target densities, iteration times and noise environments, and compared with the traditional graph signal reconstruction algorithm and the deep compressed sensing reconstruction algorithm, and then use the measured data with varying degrees of sparsity to validate. The experimental results show that the reconstructed images by this algorithm have better performance in terms of normalised mean square error, target to background ratio, reconstruction time and memory usage.

Abstract Leveraging the advanced functionalities of modern radio frequency (RF) modeling and simulation tools, specifically designed for adaptive radar processing applications, this paper presents a data‐driven approach to improve accuracy in radar target localization post adaptive radar detection. To this end, we generate a large number of radar returns by randomly placing targets of variable strengths in a predefined area, using RFView®, a high‐fidelity, site‐specific, RF modeling & simulation tool. We produce heatmap tensors from the radar returns, in range, azimuth [and Doppler], of the normalized adaptive matched filter (NAMF) test statistic. We then train a regression convolutional neural network (CNN) to estimate target locations from these heatmap tensors, and we compare the target localization accuracy of this approach with that of peak‐finding and local search methods. This empirical study shows that our regression CNN achieves a considerable improvement in target location estimation accuracy. The regression CNN offers significant gains and reasonable accuracy even at signal‐to‐clutter‐plus‐noise ratio (SCNR) regimes that are close to the breakdown threshold SCNR of the NAMF. We also study the robustness of our trained CNN to mismatches in the radar data, where the CNN is tested on heatmap tensors collected from areas that it was not trained on. We show that our CNN can be made robust to mismatches in the radar data through few‐shot learning, using a relatively small number of new training samples.

Abstract Due to the richness of natural image semantics, natural image colourisation is a challenging problem. Existing methods often suffer from semantic confusion due to insufficient semantic understanding, resulting in unreasonable colour assignments, especially at the edges of objects. This phenomenon is referred to as colour bleeding. The authors have found that using the self‐attention mechanism benefits the model's understanding and recognition of object semantics. However, this leads to another problem in colourisation, namely dull colour. With this in mind, a Position‐Spatial Attention Network(PSANet) is proposed to address the colour bleeding and the dull colour. Firstly, a novel new attention module called position‐spatial attention module (PSAM) is introduced. Through the proposed PSAM module, the model enhances the semantic understanding of images while solving the dull colour problem caused by self‐attention. Then, in order to further prevent colour bleeding on object boundaries, a gradient‐aware loss is proposed. Lastly, the colour bleeding phenomenon is further improved by the combined effect of gradient‐aware loss and edge‐aware loss. Experimental results show that this method can reduce colour bleeding largely while maintaining good perceptual quality.

Abstract Deep learning‐based face recognition models have demonstrated remarkable performance in benchmark tests, and knowledge distillation technology has been frequently accustomed to obtain high‐precision real‐time face recognition models specifically designed for mobile and embedded devices. However, in recent years, the knowledge distillation methods for face recognition, which mainly focus on feature or logit knowledge distillation techniques, neglect the attention mechanism that play an important role in the domain of neural networks. An innovation cross‐stage connection review path of the attention cosine similarity knowledge distillation method that unites the attention mechanism with review knowledge distillation method is proposed. This method transfers the attention map obtained from the teacher network to the student through a cross‐stage connection path. The efficacy and excellence of the proposed algorithm are demonstrated in popular benchmark tests.

Abstract With the development of automatic driving and path planning technology, predicting the moving trajectory of pedestrians in dynamic scenes has become one of key and urgent technical problems. However, most of the existing techniques regard all pedestrians in the scene as equally important influence on the predicted pedestrian's trajectory, and the existing methods which use sequence‐based time‐series generative models to obtain the predicted trajectories, do not allow for parallel computation, it will introduce a significant computational overhead. A new social trajectory prediction network, Social‐ATPGNN which integrates both temporal information and spatial one based on ATPGNN is proposed. In space domain, the pedestrians in the predicted scene are formed into an undirected and non fully connected graph, which solves the problem of homogenisation of pedestrian relationships, then, the spatial interaction between pedestrians is encoded to improve the accuracy of modelling pedestrian social consciousness. After acquiring high‐level spatial data, the method uses Temporal Convolutional Network which could perform parallel calculations to capture the correlation of time series of pedestrian trajectories. Through a large number of experiments, the proposed model shows the superiority over the latest models on various pedestrian trajectory datasets.

Abstract Detecting small targets in infrared images is crucial for ground surveillance and air traffic control. However, distinguishing small infrared targets from similar backgrounds is challenging due to their lack of structural and textural characteristics. To address these challenges, this study proposes a novel global information‐aware network with global interaction graph attention (GIGA) for infrared small target detection. The GIGA consists of a global interaction layer (GILayer), graph attention weights (GAW), and a global relational learning (GRL) module. Specifically, the GILayer dynamically learns global inter‐pixel relationships of small target images by enhancing the dependencies between feature dimensions. The GAW component calculates pixel‐by‐pixel similarity across the entire feature map using graph attention mechanisms, while the GRL module retains critical similarity features in the feature extraction network, thereby facilitating small target detection. Additionally, the multi‐scale context fusion module utilises self‐attention and dilation convolution to complement richer feature details at different scales. Experimental results on both natural and synthetic datasets demonstrate the proposed method's superiority over other state‐of‐the‐art conventional and deep learning approaches in infrared small target detection.

Abstract Edge devices are increasingly utilized for defect detection in power line inspection, necessitating algorithms that optimize model size and accuracy. This study introduces a lightweight detection method using the Optimized Feature Network with MobileOne‐FPN‐NASHead (OFN network) OFN network and distillation technique. The OFN incorporates a lightweight backbone, neural network search, re‐parametrization, and a feature pyramid to create a compact yet effective detection network. To enhance feature learning, a heterogeneous distillation approach is applied, leveraging a modified YOLOv8 as a teacher network. This modification includes an explicit visual centre for improved global and local information extraction, crucial for dense target detection in power line inspections. Additionally, the Minimize the points distance IoU (MPDloU) loss function is used to improve localization accuracy over the the Complete‐Intersection Over Union (CIoU) loss. Experimental results show a 1.1% mean Average Precision (mAP) increase for the enhanced YOLOv8 and a 70.2% mAP for the OFN network with 18.95 GFLOPs and 343 FPS, achieving a commendable balance between model efficiency and detection performance. The research underscores the viability of the OFN for edge computing in power line defect detection, highlighting the potential of innovative algorithmic structures in this application.

Abstract Image denoising aims to restore a clean image from a noisy image. Traditional methods utilizing convolutional neural networks (CNN) for denoising are trained using pairs of noisy and clean images to comprehend the transformation from a noisy image to a clean one. However, the acquisition of such image pairs in real‐world scenarios presents a challenge. Hence, numerous self‐supervised denoising techniques have been developed that do not require clean images for training. This study demonstrates that a straightforward loss design, concentrating on variance, can effectively train a standard CNN denoiser in a self‐supervised fashion. A novel theoretical framework is introduced for training a basic CNN denoising model using three constraints: mean, variance, and augmentation. The variance constraint is crucial as it prevents the trained model from converging to trivial solutions such as identity or zero mapping. This theory provides valuable insights for the development of new self‐supervised denoising methods. Furthermore, a method that applies this theory to proposed dual networks is developed, which consist of two standard CNN models predicting both the clean image and the noise. This approach enhances model capacity during training while minimizing computational costs during inference. This method exemplifies the implementation of the variance constraint and introduces a data constraint for dual networks. Notably, the proposed method only assumes the presence of additive white noise, irrespective of the noise distribution. This minimal assumption enhances the model's robustness against noise with complex or unknown distributions in real‐world distorted images. Experimental results indicate that the proposed Noise2Variance method exhibits commendable performance on peak signal noise ratio and structural similarity metrics compared to existing self‐supervised denoising techniques. Visual comparison of results further substantiates the efficacy of the proposed method. A comparison of model complexity reveals that the method is efficient among the compared CNN‐based techniques.

Abstract The problem of human identification through recognition of patterns in iris images captured in unconstrained environments results in image artefacts such as image occlusion and specular reflection, in which iris tissue is observable to extremely low content. To overcome this problem, this paper presents a novel method for iris image retrieval and recognition based on partial pattern matching. The main contribution of the proposed method relies on an image partitioning schema in which the iris is divided into non‐overlapping blocks with varying dimensions, facilitating the identification and removal of image regions impaired by eyelids, eyelashes, and specular reflections. In fact, the blocks that contain artefacts are completely ignored and those blocks are preserved that include useful patterns for identification. In addition, a multi‐feature similarity followed by a score fusion technique is employed for ranking the retrieval results. The remarkable results of the classification stage include an accuracy of 100%, 98.75%, and 99.94% on three benchmark databases, including UPOL, UBIRIS.V2, and CASIA‐Iris‐Interval.v3, respectively. Additionally, in the retrieval stage, the proposed method achieves a precision of 100% on all three benchmark databases, a recall of 83.33%, and a F1‐measure of 90.91 on the CASIA‐Iris‐Interval.v3 dataset.

Abstract Semantic segmentation of underwater fish images is vital for monitoring fish stocks, assessing marine resources, and sustaining fisheries. To tackle challenges such as low segmentation accuracy, inadequate real‐time performance, and imprecise location segmentation in current methods, a novel lightweight U‐Net model is proposed. The proposed model acquires more segmentation details by applying a multiple‐input approach at the first four encoder levels. To achieve both lightweight and high accuracy, a multi‐scale residual structure (MRS) module is proposed to reduce parameters and compensate for the accuracy loss caused by the reduction of channels. To improve segmentation accuracy, a multi‐scale skip connection (MSC) structure is further proposed, and the convolution block attention mechanism (CBAM) is introduced at the end of each decoder level for weight adjustment. Experimental results demonstrate a notable reduction in model volume, parameters, and floating‐point operations by 94.20%, 94.39%, and 51.52% respectively, compared to the original model. The proposed model achieves a high mean intersection over union (mIOU) of 94.44%, mean pixel accuracy (mPA) of 97.03%, and a frame rate of 43.62 frames per second (FPS). With its high precision and minimal parameters, the model strikes a balance between accuracy and speed, making it particularly suitable for underwater image segmentation.

Abstract Presently, State Space Models (SSMs), including frameworks like Mamba, have been incorporated into the realm of computer vision. These models not only sustain remote interactions and encapsulate global semantic information effectively, but also preserve linear computational complexity, offering a balance between performance and computational efficiency. Given that Mamba inherently adheres to the principle of selectivity when constructing sequence models, the goal is to further unleash the potential of Mamba through this innovative combination of convolution and self‐attention, improve accuracy and minimize the number of parameters while achieving linear complexity. Mamba is employed as an encoder to distill semantic information from the image, and it is supplemented with convolutional blocks, thereby conserving the details of the image. Concurrently, embedding prompts at a deeper level enhances its adaptability to cater to diverse requirements. Lastly, a bidirectional attention mechanism is incorporated for inference, striving to retain both global connections and local details to the maximum extent. This culminates in a novel, lightweight medical segmentation model. Exhaustive experiments were executed on six public datasets. The empirical results show that the proposed model exhibits competitive performance in medical image segmentation tasks.

Abstract Accurately identifying tropical fish serves as a crucial indicator, offering an insight into the state of marine biodiversity and the condition of coral reef ecosystems. However, the current detection networks are prone to omission and misidentification due to occlusion between fish and the complex underwater environment. This paper proposes a modified approach named FishFocusNet, in which alterable kernel convolution modules, asymptotic feature pyramid network (AFPN), and Shape‐IoU are integrated into YOLOv8. To extract a more comprehensive set of fish features, AKConv modules with arbitrary kernel sizes are proposed to take the place of the conventional fixed‐shaped kernels in the backbone for downsampling. AFPN is adopted as the feature integration structure in the neck, which enhances feature fusion and adaptive spatial fusion between non‐adjacent layers. In the detector head, Shape‐IoU is employed to achieve precise localization of fish targets. The superiorities of these modifications are proved by ablation experiments and comparative experiments. The experimental results show that the optimized approach obtained an mAP of 81.8% accompanied by 2.4 MB parameters and 3.6 GB FLOPS. Meanwhile, compared with more complicated models of similar scale, the proposed method can enhance recognition accuracy to 84.2% and significantly reduce computational costs.

Abstract The high‐precision visual perception results are easily affected by the lens flare issue when the image sensor is facing to strong light. The existing flare removal methods have poor robustness when confronted with flare interference caused by complex nighttime lighting, which has to preserve natural light source information. A simulated dataset for the removal of night flares is created to solve the problem of collecting complete paired training data, and night flare removal network (NFR‐Net) is proposed to remove the interference caused by various light disturbances at night. The light source extraction module is introduced to retain light source information realistically and effectively in night vision scenes. Extensive experimental results demonstrate that the proposed method is superior to the existing related methods in the various complex night vision scenes. The proposed NFR‐Net can enhance visual perception of nighttime images significantly and improve the performance of night vision tasks.

Abstract The complex nature of human brain tissues is important in ensuring accurate diagnosis to save human lives. Research on early detection of brain diseases has gained significant prominence within medical intelligence using highly complex model architectures with only a single label that cannot be verified. This paper introduces an innovative approach to Siamese Network Genetic Algorithm (SN‐GA) leveraging Siamese contrastive learning for classifying brain images across diverse diseases. Our core architecture is a Bi‐Convolutional Neural Network (Bi‐CNN) optimized by a genetic algorithm to enhance brain image classification. Specifically, five widely recognized transfer learning‐based architectures, namely AlexNet, Efficient‐B0, VGG‐16, ResNet‐50, and Inception‐v3, have been incorporated to evaluate the effectiveness of the proposed SN‐GA system. The performance of these models has been rigorously analyzed and compared using two distinct datasets: Brain tumors and Alzheimer's datasets. The experimental results robustly affirm the efficacy of the proposed Siamese model, yielding exceptional levels of accuracy, precision, and recall, all peaking at 97%. These findings underscore the potential and resilience of the optimized Siamese network in the context of brain disease classification, emphasizing its significance in advancing the field of medical imaging and diagnosis, with implications for early intervention and patient care.

Abstract Cardiac hemangioma is a rare benign tumour that presents diagnostic challenges due to its variable clinical symptoms, imaging features, and locations. This study proposes a novel segmentation method based on a Convolutional Neural Network (CNN) and Transformer integration, with Swin‐UNet as the core model. We incorporated a U‐shaped convolutional neural network block into the original jump connection of Swin‐UNet. The Binary Cross Entropy Loss (BCE Loss) algorithm was added, and the learning rate decay algorithm was modified to select the appropriate one by comparing loss values. This paper utilizes the publicly available cardiac angioma dataset in AI Studio, consisting of 215 images for training and testing. To evaluate the effectiveness of the proposed model, this paper demonstrates its optimality through ablation experiments and comparisons with other mainstream models. The comparison experiments show that this model improves Dice by approximately 12%, HD95 by approximately 4.7 mm, Accuracy by approximately 6.1%, and F1 score by 0.11 compared to models such as UNet, UNet++, and Deeplabv3+, etc. For the recently proposed SOTO models, such as TransUNet, Swin‐UNet, and MultiResUnet, the Dice score improved by about 1.2%, HD95 reduced by about 1mm, Accuracy improved by about 0.3%, and F1 score improved by 0.015.

Abstract Aiming at the problems of low detection accuracy, high computational complexity and long‐time consumption of visual perception model in a complex mining environment, this research designs a visual information perception system of coal mine comprehensive excavation working face for an edge computing terminal. Firstly, the C3‐Fast feature extraction module, spatial pyramid pooling with cross‐stage partial connection (SPPCSPC) pooling module, bi‐directional feature pyramid network and lightweight decoupled detection head are used to optimize the YOLOv5s model, so as to construct the FSBD‐YOLOv5s multi‐object detection model. Secondly, the pruning and distillation algorithm is used to lighten the FSBD‐YOLOv5s model, and the model complexity is greatly reduced while maintaining the model detection accuracy. Further, the lightweight FSBD‐YOLOv5s model is migrated and deployed to the edge computing terminal platform and the TensorRT engine is used to accelerate model inference. Finally, experiments are carried out based on the data set of the coal mine comprehensive excavation working face. The experimental results show that on the edge computing terminal platform, the parameters and computational volume of the lightweight FSBD‐YOLOv5s model are reduced by 50.8% and 34.0%, while its detection accuracy and speed reach 94.0% and 43.7 fps, which can fully satisfy the requirements of the accuracy and real‐time for the coal mine engineering applications.

Abstract Driving while inattentive or fatigued significantly contributes to traffic accidents and puts road users at a significantly higher risk of collision. The rise in road accidents due to driver inattention resulting from distractive objects, for example, mobile phones, drinking, or tiredness, requires intelligent traffic monitoring systems to promote road safety. However, outdated detection technologies cannot handle the poor accuracy and the lack of real‐time processing possibility especially when combined with the variations of driving environment. This paper introduces “ME‐YOLOv8” which operates driver`s distraction and fatigue through a modified version of YOLOv8, which includes modules multi‐head self‐attention (MHSA) and efficient channel attention (ECA) modules applied, where the goal of MHSA is to improve the sensitivity of global features and the ECA attentions focus on critical features. Additionally, a dataset was created containing 3660 images covering multiple distracted and drowsy driver scenarios. The results reflect the enhanced detection capabilities of ME‐YOLOv8 and demonstrate its effectiveness in real‐time scenarios. This study demonstrates a significant advancement in the application of AI to public safety and highlights the critical role that state‐of‐the‐art deep learning algorithms play in lowering the risks associated with distracted and tired driving.

Abstract Predicting traffic flow is vital for optimizing transportation efficiency, reducing fuel consumption, and minimizing commute times. While artificial intelligence tools have been effective in addressing this, there have been some difficulties in processing spatial and temporal data. Current transformer‐based methods, although cutting‐edge for traffic prediction, encounter challenges with handling long sequences and capturing temporal relations effectively. Addressing these, the research introduces a model combining multi‐scale attention modules within transformer layers. This model employs spatio‐temporal transformer blocks, enriched with multi‐scale convolutional attention mechanisms, allowing for a deeper understanding of temporal and spatial traffic patterns. This unique attention mechanism enhances data feature interpretation, leading to heightened prediction precision. The tests on extensive traffic datasets showcase the model's prowess in capturing both local and global traffic features, resulting in superior traffic status predictions. In summary, the innovative model offers an efficacious approach to long‐sequence traffic data learning and temporal relationship extraction, setting a new benchmark in traffic flow prediction accuracy.

Abstract It is difficult to identify an arc fault accurately when the loads on the user side are more complicated, which hinders the development of low‐voltage monitoring and pre‐warning inspection. This study acquired a series of arc‐fault signals according to IEC 62606. The main time‐frequency features were strengthened with high efficiency by applying the generalized S‐transform to them with a bi‐Gaussian window. Further, the power spectrum density determination allowed for the detection of imperceptible high‐frequency harmonic energy reflections, thus increasing the rate of arc‐fault diagnosis and making it suitable for arc‐fault monitoring of non‐linear loads. The final samples were trained and classified using a 2D convolutional neural network and the overall accuracy of identification was observed to be 98.13%, which involved various domestic loads, thus providing a reference for follow‐up arc‐fault monitoring and inspection research.

Abstract Bird‐related outages greatly threaten the safety of overhead transmission and distribution lines, while electrocution and collisions of birds with power lines, especially endangered species, are significant environmental concerns. Automatic bird recognition can be helpful to mitigate this contradiction. This paper proposes a method for automatic classification of bird species related to power line faults combining deep convolution features with error‐correcting output codes support vector machine (ECOC‐SVM). An image dataset of about 20 high‐risk and 20 low‐risk bird species was constructed, and the feed‐forward denoising convolutional neural network was used for image preprocessing. The deep convolution features of bird images were extracted by DarkNet‐53, and taken as inputs of the ECOC‐SVM for model training and bird species classification. The gradient‐weighted class activation mapping was used for visual explanations of the model decision region. The experimental results indicate that the average accuracy of the proposed method can reach 94.39%, and its performance was better than other models using different feature extraction networks and classification algorithms.

Abstract Electrical impedance tomography (EIT) is a promising non‐invasive imaging technique that visualizes the electrical conductivity of an anatomic structure to form based on measured boundary voltages. However, the EIT inverse problem for the image reconstruction is nonlinear and highly ill‐posed. Therefore, in this work, a simulated dataset that mimics the human thorax was generated with boundary voltages based on given conductivity distributions. To overcome the challenges of image reconstruction, an ensemble learning method was proposed. The ensemble method combines several convolutional neural network models, which are the simple Convolutional Neural Network (CNN) model, AlexNet, AlexNet with residual block, and the modified AlexNet model. The ensemble models’ weights selection was based on average technique giving the best coefficient of determination (R2 score). The reconstruction quality is quantitatively evaluated by calculating the root mean square error (RMSE), the coefficient of determination (R2 score), and the image correlation coefficient (ICC). The proposed method's best performance is an RMSE of 0.09404, an R2 score of 0.926186, and an ICC of 0.95783 using an ensemble model. The proposed method is promising as it can construct valuable images for clinical EIT applications and measurements compared to previous studies.

Abstract In recent years, deep learning methods were good solutions for object detection in synthetic aperture radar (SAR) images. However, the problems of complex scenarios, large object scale differences and imperfect fine‐grained classification in ship detection were intractable. In response, an improved model GDB‐YOLOv5s (Improved YOLOv5s model incorporating global attention mechanism (GAM), DCN‐v2 and BiFusion) is designed. This model introduces deformable convolution networks (DCN‐v2) into the Backbone to enhance the adaptability of the receptive field. It replaces the original Neck's PANet structure with a BiFusion structure to better fuse the extracted multiscale features. Additionally, it integrates GAM into the network to reduce information loss and improve global feature interaction. Experiments were conducted on single‐class dataset SSDD and multi‐class dataset SRSSD‐V1.0. The results show that the GDB‐YOLOv5s model improves mean average precision scores (mAP) significantly, outperforming the original YOLOv5s model and other traditional methods. GDB‐YOLOv5s also improves Precision‐score (P) and Recall‐score (R) for fine‐grained classification to some extent, thereby reducing false alarms and missed detections. It has been proved that the improved model is relatively effective.