Convolutional neural networks(CNNs)-based medical image segmentation technologies have been widely used in medical image segmentation because of their strong representation and generalization abilities.However,due to ...Convolutional neural networks(CNNs)-based medical image segmentation technologies have been widely used in medical image segmentation because of their strong representation and generalization abilities.However,due to the inability to effectively capture global information from images,CNNs can easily lead to loss of contours and textures in segmentation results.Notice that the transformer model can effectively capture the properties of long-range dependencies in the image,and furthermore,combining the CNN and the transformer can effectively extract local details and global contextual features of the image.Motivated by this,we propose a multi-branch and multi-scale attention network(M2ANet)for medical image segmentation,whose architecture consists of three components.Specifically,in the first component,we construct an adaptive multi-branch patch module for parallel extraction of image features to reduce information loss caused by downsampling.In the second component,we apply residual block to the well-known convolutional block attention module to enhance the network’s ability to recognize important features of images and alleviate the phenomenon of gradient vanishing.In the third component,we design a multi-scale feature fusion module,in which we adopt adaptive average pooling and position encoding to enhance contextual features,and then multi-head attention is introduced to further enrich feature representation.Finally,we validate the effectiveness and feasibility of the proposed M2ANet method through comparative experiments on four benchmark medical image segmentation datasets,particularly in the context of preserving contours and textures.展开更多
The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image...The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image SR may lead to issues such as blurry details and excessive smoothness.To address the limitations,we proposed an algorithm based on the generative adversarial network(GAN)framework.In the generator network,three different sizes of convolutions connected by a residual dense structure were used to extract detailed features,and an attention mechanism combined with dual channel and spatial information was applied to concentrate the computing power on crucial areas.In the discriminator network,using InstanceNorm to normalize tensors sped up the training process while retaining feature information.The experimental results demonstrate that our algorithm achieves higher peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM)compared to other methods,resulting in an improved visual quality.展开更多
Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address ...Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.展开更多
Multimodal image fusion plays an important role in image analysis and applications.Multimodal medical image fusion helps to combine contrast features from two or more input imaging modalities to represent fused inform...Multimodal image fusion plays an important role in image analysis and applications.Multimodal medical image fusion helps to combine contrast features from two or more input imaging modalities to represent fused information in a single image.One of the critical clinical applications of medical image fusion is to fuse anatomical and functional modalities for rapid diagnosis of malignant tissues.This paper proposes a multimodal medical image fusion network(MMIF-Net)based on multiscale hybrid attention.The method first decomposes the original image to obtain the low-rank and significant parts.Then,to utilize the features at different scales,we add amultiscalemechanism that uses three filters of different sizes to extract the features in the encoded network.Also,a hybrid attention module is introduced to obtain more image details.Finally,the fused images are reconstructed by decoding the network.We conducted experiments with clinical images from brain computed tomography/magnetic resonance.The experimental results show that the multimodal medical image fusion network method based on multiscale hybrid attention works better than other advanced fusion methods.展开更多
This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualiz...This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement.However,fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging.To deal with this problem,we propose a 3D multi-scale attention VoxelMorph(MAVoxelMorph)registration network.To alleviate the large deformation problem,a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction,and position-aware axial attention for long-distance dependencies between pixels capture.To further improve the large deformation and fine structure registration results,a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers.Our method was evaluated on four public lung datasets(DIR-Lab dataset,Creatis dataset,Learn2Reg dataset,OASIS dataset)and a local dataset.Results proved that the proposed method achieved better registration performance than current state-of-the-art methods,especially in handling the registration of large deformations and fine structures.It also proved to be fast in 3D image registration,using about 1.5 s,and faster than most methods.Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries.展开更多
Accurate diagnosis of apple leaf diseases is crucial for improving the quality of apple production and promoting the development of the apple industry. However, apple leaf diseases do not differ significantly from ima...Accurate diagnosis of apple leaf diseases is crucial for improving the quality of apple production and promoting the development of the apple industry. However, apple leaf diseases do not differ significantly from image texture and structural information. The difficulties in disease feature extraction in complex backgrounds slow the related research progress. To address the problems, this paper proposes an improved multi-scale inverse bottleneck residual network model based on a triplet parallel attention mechanism, which is built upon ResNet-50, while improving and combining the inception module and ResNext inverse bottleneck blocks, to recognize seven types of apple leaf(including six diseases of alternaria leaf spot, brown spot, grey spot, mosaic, rust, scab, and one healthy). First, the 3×3 convolutions in some of the residual modules are replaced by multi-scale residual convolutions, the convolution kernels of different sizes contained in each branch of the multi-scale convolution are applied to extract feature maps of different sizes, and the outputs of these branches are multi-scale fused by summing to enrich the output features of the images. Second, the global layer-wise dynamic coordinated inverse bottleneck structure is used to reduce the network feature loss. The inverse bottleneck structure makes the image information less lossy when transforming from different dimensional feature spaces. The fusion of multi-scale and layer-wise dynamic coordinated inverse bottlenecks makes the model effectively balances computational efficiency and feature representation capability, and more robust with a combination of horizontal and vertical features in the fine identification of apple leaf diseases. Finally, after each improved module, a triplet parallel attention module is integrated with cross-dimensional interactions among channels through rotations and residual transformations, which improves the parallel search efficiency of important features and the recognition rate of the network with relatively small computational costs while the dimensional dependencies are improved. To verify the validity of the model in this paper, we uniformly enhance apple leaf disease images screened from the public data sets of Plant Village, Baidu Flying Paddle, and the Internet. The final processed image count is 14,000. The ablation study, pre-processing comparison, and method comparison are conducted on the processed datasets. The experimental results demonstrate that the proposed method reaches 98.73% accuracy on the adopted datasets, which is 1.82% higher than the classical ResNet-50 model, and 0.29% better than the apple leaf disease datasets before preprocessing. It also achieves competitive results in apple leaf disease identification compared to some state-ofthe-art methods.展开更多
Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD)...Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD).Recently,an increasing number of studies have focused on employing deep learning techniques to analyze FC patterns for brain disease classification.However,the high dimensionality of the FC features and the interpretation of deep learning results are issues that need to be addressed in the FC-based brain disease classification.In this paper,we proposed a multi-scale attention-based deep neural network(MSA-DNN)model to classify FC patterns for the ASD diagnosis.The model was implemented by adding a flexible multi-scale attention(MSA)module to the auto-encoder based backbone DNN,which can extract multi-scale features of the FC patterns and change the level of attention for different FCs by continuous learning.Our model will reinforce the weights of important FC features while suppress the unimportant FCs to ensure the sparsity of the model weights and enhance the model interpretability.We performed systematic experiments on the large multi-sites ASD dataset with both ten-fold and leaveone-site-out cross-validations.Results showed that our model outperformed classical methods in brain disease classification and revealed robust intersite prediction performance.We also localized important FC features and brain regions associated with ASD classification.Overall,our study further promotes the biomarker detection and computer-aided classification for ASD diagnosis,and the proposed MSA module is flexible and easy to implement in other classification networks.展开更多
Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate resul...Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate results.Most deep learning-based BAA methods feed the extracted critical points of images into the network by providing additional annotations.This operation is costly and subjective.To address these problems,we propose a multi-scale attentional densely connected network(MSADCN)in this paper.MSADCN constructs a multi-scale dense connectivity mechanism,which can avoid overfitting,obtain the local features effectively and prevent gradient vanishing even in limited training data.First,MSADCN designs multi-scale structures in the densely connected network to extract fine-grained features at different scales.Then,coordinate attention is embedded to focus on critical features and automatically locate the regions of interest(ROI)without additional annotation.In addition,to improve the model’s generalization,transfer learning is applied to train the proposed MSADCN on the public dataset IMDB-WIKI,and the obtained pre-trained weights are loaded onto the Radiological Society of North America(RSNA)dataset.Finally,label distribution learning(LDL)and expectation regression techniques are introduced into our model to exploit the correlation between hand bone images of different ages,which can obtain stable age estimates.Extensive experiments confirm that our model can converge more efficiently and obtain a mean absolute error(MAE)of 4.64 months,outperforming some state-of-the-art BAA methods.展开更多
Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we ...Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we propose a new generative adversarial network(GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention(SA) module with an implicit Laplacian offset attention(OA) module and to aggregate the adjacency features using a multiscale offset attention(MSOA)module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention(RMSOA) module, which utilizes multiscale structural relationships to generate finer details. Result The results of several experiments show that our method outperforms existing methods and is highly robust.展开更多
Time series data is a kind of data accumulated over time,which can describe the change of phenomenon.This kind of data reflects the degree of change of a certain thing or phenomenon.The existing technologies such as L...Time series data is a kind of data accumulated over time,which can describe the change of phenomenon.This kind of data reflects the degree of change of a certain thing or phenomenon.The existing technologies such as LSTM and ARIMA are better than convolutional neural network in time series prediction,but they are not enough to mine the periodicity of data.In this article,we perform periodic analysis on two types of time series data,select time metrics with high periodic characteristics,and propose a multi-scale prediction model based on the attention mechanism for the periodic trend of the data.A loss calculation method for traffic time series characteristics is proposed as well.Multiple experiments have been conducted on actual data sets.The experiments show that the method proposed in this paper has better performance than commonly used traffic prediction methods(ARIMA,LSTM,etc.)and 3%-5%increase on MAPE.展开更多
Background The use of remote photoplethysmography(rPPG)to estimate blood volume pulse in a noncontact manner has been an active research topic in recent years.Existing methods are primarily based on a singlescale regi...Background The use of remote photoplethysmography(rPPG)to estimate blood volume pulse in a noncontact manner has been an active research topic in recent years.Existing methods are primarily based on a singlescale region of interest(ROI).However,some noise signals that are not easily separated in a single-scale space can be easily separated in a multi-scale space.Also,existing spatiotemporal networks mainly focus on local spatiotemporal information and do not emphasize temporal information,which is crucial in pulse extraction problems,resulting in insufficient spatiotemporal feature modelling.Methods Here,we propose a multi-scale facial video pulse extraction network based on separable spatiotemporal convolution(SSTC)and dimension separable attention(DSAT).First,to solve the problem of a single-scale ROI,we constructed a multi-scale feature space for initial signal separation.Second,SSTC and DSAT were designed for efficient spatiotemporal correlation modeling,which increased the information interaction between the long-span time and space dimensions;this placed more emphasis on temporal features.Results The signal-to-noise ratio(SNR)of the proposed network reached 9.58dB on the PURE dataset and 6.77dB on the UBFC-rPPG dataset,outperforming state-of-the-art algorithms.Conclusions The results showed that fusing multi-scale signals yielded better results than methods based on only single-scale signals.The proposed SSTC and dimension-separable attention mechanism will contribute to more accurate pulse signal extraction.展开更多
In light of the prevailing issue that the existing convolutional neural network(CNN)power quality disturbance identification method can only extract single-scale features,which leads to a lack of feature information a...In light of the prevailing issue that the existing convolutional neural network(CNN)power quality disturbance identification method can only extract single-scale features,which leads to a lack of feature information and weak anti-noise performance,a new approach for identifying power quality disturbances based on an adaptive Kalman filter(KF)and multi-scale channel attention(MS-CAM)fused convolutional neural network is suggested.Single and composite-disruption signals are generated through simulation.The adaptive maximum likelihood Kalman filter is employed for noise reduction in the initial disturbance signal,and subsequent integration of multi-scale features into the conventional CNN architecture is conducted.The multi-scale features of the signal are captured by convolution kernels of different sizes so that the model can obtain diverse feature expressions.The attention mechanism(ATT)is introduced to adaptively allocate the extracted features,and the features are fused and selected to obtain the new main features.The Softmax classifier is employed for the classification of power quality disturbances.Finally,by comparing the recognition accuracy of the convolutional neural network(CNN),the model using the attention mechanism,the bidirectional long-term and short-term memory network(MS-Bi-LSTM),and the multi-scale convolutional neural network(MSCNN)with the attention mechanism with the proposed method.The simulation results demonstrate that the proposed method is higher than CNN,MS-Bi-LSTM,and MSCNN,and the overall recognition rate exceeds 99%,and the proposed method has significant classification accuracy and robust classification performance.This achievement provides a new perspective for further exploration in the field of power quality disturbance classification.展开更多
With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods ...With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.展开更多
Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and text...Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.展开更多
Due to their high mechanical compliance and excellent biocompatibility,conductive hydrogels exhibit significant potential for applications in flexible electronics.However,as the demand for high sensitivity,superior me...Due to their high mechanical compliance and excellent biocompatibility,conductive hydrogels exhibit significant potential for applications in flexible electronics.However,as the demand for high sensitivity,superior mechanical properties,and strong adhesion performance continues to grow,many conventional fabrication methods remain complex and costly.Herein,we propose a simple and efficient strategy to construct an entangled network hydrogel through a liquid-metal-induced cross-linking reaction,hydrogel demonstrates outstanding properties,including exceptional stretchability(1643%),high tensile strength(366.54 kPa),toughness(350.2 kJ m^(−3)),and relatively low mechanical hysteresis.The hydrogel exhibits long-term stable reusable adhesion(104 kPa),enabling conformal and stable adhesion to human skin.This capability allows it to effectively capture high-quality epidermal electrophysiological signals with high signal-to-noise ratio(25.2 dB)and low impedance(310 ohms).Furthermore,by integrating advanced machine learning algorithms,achieving an attention classification accuracy of 91.38%,which will significantly impact fields like education,healthcare,and artificial intelligence.展开更多
Convolutional neural network(CNN)with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global featu...Convolutional neural network(CNN)with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global feature.The transformer can extract the global information well but adapting it to small medical datasets is challenging and its computational complexity can be heavy.In this work,a serial and parallel network is proposed for the accurate 3D medical image segmentation by combining CNN and transformer and promoting feature interactions across various semantic levels.The core components of the proposed method include the cross window self-attention based transformer(CWST)and multi-scale local enhanced(MLE)modules.The CWST module enhances the global context understanding by partitioning 3D images into non-overlapping windows and calculating sparse global attention between windows.The MLE module selectively fuses features by computing the voxel attention between different branch features,and uses convolution to strengthen the dense local information.The experiments on the prostate,atrium,and pancreas MR/CT image datasets consistently demonstrate the advantage of the proposed method over six popular segmentation models in both qualitative evaluation and quantitative indexes such as dice similarity coefficient,Intersection over Union,95%Hausdorff distance and average symmetric surface distance.展开更多
In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accurac...In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.展开更多
In this paper,we propose hierarchical attention dual network(DNet)for fine-grained image classification.The DNet can randomly select pairs of inputs from the dataset and compare the differences between them through hi...In this paper,we propose hierarchical attention dual network(DNet)for fine-grained image classification.The DNet can randomly select pairs of inputs from the dataset and compare the differences between them through hierarchical attention feature learning,which are used simultaneously to remove noise and retain salient features.In the loss function,it considers the losses of difference in paired images according to the intra-variance and inter-variance.In addition,we also collect the disaster scene dataset from remote sensing images and apply the proposed method to disaster scene classification,which contains complex scenes and multiple types of disasters.Compared to other methods,experimental results show that the DNet with hierarchical attention is robust to different datasets and performs better.展开更多
Aiming at the problems of low detection accuracy and large model size of existing object detection algorithms applied to complex road scenes,an improved you only look once version 8(YOLOv8)object detection algorithm f...Aiming at the problems of low detection accuracy and large model size of existing object detection algorithms applied to complex road scenes,an improved you only look once version 8(YOLOv8)object detection algorithm for infrared images,F-YOLOv8,is proposed.First,a spatial-to-depth network replaces the traditional backbone network's strided convolution or pooling layer.At the same time,it combines with the channel attention mechanism so that the neural network focuses on the channels with large weight values to better extract low-resolution image feature information;then an improved feature pyramid network of lightweight bidirectional feature pyramid network(L-BiFPN)is proposed,which can efficiently fuse features of different scales.In addition,a loss function of insertion of union based on the minimum point distance(MPDIoU)is introduced for bounding box regression,which obtains faster convergence speed and more accurate regression results.Experimental results on the FLIR dataset show that the improved algorithm can accurately detect infrared road targets in real time with 3%and 2.2%enhancement in mean average precision at 50%IoU(mAP50)and mean average precision at 50%—95%IoU(mAP50-95),respectively,and 38.1%,37.3%and 16.9%reduction in the number of model parameters,the model weight,and floating-point operations per second(FLOPs),respectively.To further demonstrate the detection capability of the improved algorithm,it is tested on the public dataset PASCAL VOC,and the results show that F-YOLO has excellent generalized detection performance.展开更多
基金supported by the Natural Science Foundation of the Anhui Higher Education Institutions of China(Grant Nos.2023AH040149 and 2024AH051915)the Anhui Provincial Natural Science Foundation(Grant No.2208085MF168)+1 种基金the Science and Technology Innovation Tackle Plan Project of Maanshan(Grant No.2024RGZN001)the Scientific Research Fund Project of Anhui Medical University(Grant No.2023xkj122).
文摘Convolutional neural networks(CNNs)-based medical image segmentation technologies have been widely used in medical image segmentation because of their strong representation and generalization abilities.However,due to the inability to effectively capture global information from images,CNNs can easily lead to loss of contours and textures in segmentation results.Notice that the transformer model can effectively capture the properties of long-range dependencies in the image,and furthermore,combining the CNN and the transformer can effectively extract local details and global contextual features of the image.Motivated by this,we propose a multi-branch and multi-scale attention network(M2ANet)for medical image segmentation,whose architecture consists of three components.Specifically,in the first component,we construct an adaptive multi-branch patch module for parallel extraction of image features to reduce information loss caused by downsampling.In the second component,we apply residual block to the well-known convolutional block attention module to enhance the network’s ability to recognize important features of images and alleviate the phenomenon of gradient vanishing.In the third component,we design a multi-scale feature fusion module,in which we adopt adaptive average pooling and position encoding to enhance contextual features,and then multi-head attention is introduced to further enrich feature representation.Finally,we validate the effectiveness and feasibility of the proposed M2ANet method through comparative experiments on four benchmark medical image segmentation datasets,particularly in the context of preserving contours and textures.
文摘The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image SR may lead to issues such as blurry details and excessive smoothness.To address the limitations,we proposed an algorithm based on the generative adversarial network(GAN)framework.In the generator network,three different sizes of convolutions connected by a residual dense structure were used to extract detailed features,and an attention mechanism combined with dual channel and spatial information was applied to concentrate the computing power on crucial areas.In the discriminator network,using InstanceNorm to normalize tensors sped up the training process while retaining feature information.The experimental results demonstrate that our algorithm achieves higher peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM)compared to other methods,resulting in an improved visual quality.
基金supported by the National Natural Science Foundation of China(Grant Nos.62472149,62376089,62202147)Hubei Provincial Science and Technology Plan Project(2023BCB04100).
文摘Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.
基金supported by Qingdao Huanghai University School-Level ScientificResearch Project(2023KJ14)Undergraduate Teaching Reform Research Project of Shandong Provincial Department of Education(M2022328)+1 种基金National Natural Science Foundation of China under Grant(42472324)Qingdao Postdoctoral Foundation under Grant(QDBSH202402049).
文摘Multimodal image fusion plays an important role in image analysis and applications.Multimodal medical image fusion helps to combine contrast features from two or more input imaging modalities to represent fused information in a single image.One of the critical clinical applications of medical image fusion is to fuse anatomical and functional modalities for rapid diagnosis of malignant tissues.This paper proposes a multimodal medical image fusion network(MMIF-Net)based on multiscale hybrid attention.The method first decomposes the original image to obtain the low-rank and significant parts.Then,to utilize the features at different scales,we add amultiscalemechanism that uses three filters of different sizes to extract the features in the encoded network.Also,a hybrid attention module is introduced to obtain more image details.Finally,the fused images are reconstructed by decoding the network.We conducted experiments with clinical images from brain computed tomography/magnetic resonance.The experimental results show that the multimodal medical image fusion network method based on multiscale hybrid attention works better than other advanced fusion methods.
基金supported in part by the National Natural Science Foundation of China[62301374]Hubei Provincial Natural Science Foundation of China[2022CFB804]+2 种基金Hubei Provincial Education Research Project[B2022057]the Youths Science Foundation of Wuhan Institute of Technology[K202240]the 15th Graduate Education Innovation Fund of Wuhan Institute of Technology[CX2023295].
文摘This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement.However,fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging.To deal with this problem,we propose a 3D multi-scale attention VoxelMorph(MAVoxelMorph)registration network.To alleviate the large deformation problem,a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction,and position-aware axial attention for long-distance dependencies between pixels capture.To further improve the large deformation and fine structure registration results,a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers.Our method was evaluated on four public lung datasets(DIR-Lab dataset,Creatis dataset,Learn2Reg dataset,OASIS dataset)and a local dataset.Results proved that the proposed method achieved better registration performance than current state-of-the-art methods,especially in handling the registration of large deformations and fine structures.It also proved to be fast in 3D image registration,using about 1.5 s,and faster than most methods.Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries.
基金supported in part by the General Program Hunan Provincial Natural Science Foundation of 2022,China(2022JJ31022)the Undergraduate Education Reform Project of Hunan Province,China(HNJG-20210532)the National Natural Science Foundation of China(62276276)。
文摘Accurate diagnosis of apple leaf diseases is crucial for improving the quality of apple production and promoting the development of the apple industry. However, apple leaf diseases do not differ significantly from image texture and structural information. The difficulties in disease feature extraction in complex backgrounds slow the related research progress. To address the problems, this paper proposes an improved multi-scale inverse bottleneck residual network model based on a triplet parallel attention mechanism, which is built upon ResNet-50, while improving and combining the inception module and ResNext inverse bottleneck blocks, to recognize seven types of apple leaf(including six diseases of alternaria leaf spot, brown spot, grey spot, mosaic, rust, scab, and one healthy). First, the 3×3 convolutions in some of the residual modules are replaced by multi-scale residual convolutions, the convolution kernels of different sizes contained in each branch of the multi-scale convolution are applied to extract feature maps of different sizes, and the outputs of these branches are multi-scale fused by summing to enrich the output features of the images. Second, the global layer-wise dynamic coordinated inverse bottleneck structure is used to reduce the network feature loss. The inverse bottleneck structure makes the image information less lossy when transforming from different dimensional feature spaces. The fusion of multi-scale and layer-wise dynamic coordinated inverse bottlenecks makes the model effectively balances computational efficiency and feature representation capability, and more robust with a combination of horizontal and vertical features in the fine identification of apple leaf diseases. Finally, after each improved module, a triplet parallel attention module is integrated with cross-dimensional interactions among channels through rotations and residual transformations, which improves the parallel search efficiency of important features and the recognition rate of the network with relatively small computational costs while the dimensional dependencies are improved. To verify the validity of the model in this paper, we uniformly enhance apple leaf disease images screened from the public data sets of Plant Village, Baidu Flying Paddle, and the Internet. The final processed image count is 14,000. The ablation study, pre-processing comparison, and method comparison are conducted on the processed datasets. The experimental results demonstrate that the proposed method reaches 98.73% accuracy on the adopted datasets, which is 1.82% higher than the classical ResNet-50 model, and 0.29% better than the apple leaf disease datasets before preprocessing. It also achieves competitive results in apple leaf disease identification compared to some state-ofthe-art methods.
基金This work was supported by the National Natural Science Foundation of China(No.61906006).
文摘Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD).Recently,an increasing number of studies have focused on employing deep learning techniques to analyze FC patterns for brain disease classification.However,the high dimensionality of the FC features and the interpretation of deep learning results are issues that need to be addressed in the FC-based brain disease classification.In this paper,we proposed a multi-scale attention-based deep neural network(MSA-DNN)model to classify FC patterns for the ASD diagnosis.The model was implemented by adding a flexible multi-scale attention(MSA)module to the auto-encoder based backbone DNN,which can extract multi-scale features of the FC patterns and change the level of attention for different FCs by continuous learning.Our model will reinforce the weights of important FC features while suppress the unimportant FCs to ensure the sparsity of the model weights and enhance the model interpretability.We performed systematic experiments on the large multi-sites ASD dataset with both ten-fold and leaveone-site-out cross-validations.Results showed that our model outperformed classical methods in brain disease classification and revealed robust intersite prediction performance.We also localized important FC features and brain regions associated with ASD classification.Overall,our study further promotes the biomarker detection and computer-aided classification for ASD diagnosis,and the proposed MSA module is flexible and easy to implement in other classification networks.
基金This research is partially supported by grant from the National Natural Science Foundation of China(No.72071019)grant from the Natural Science Foundation of Chongqing(No.cstc2021jcyj-msxmX0185)grant from the Chongqing Graduate Education and Teaching Reform Research Project(No.yjg193096).
文摘Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate results.Most deep learning-based BAA methods feed the extracted critical points of images into the network by providing additional annotations.This operation is costly and subjective.To address these problems,we propose a multi-scale attentional densely connected network(MSADCN)in this paper.MSADCN constructs a multi-scale dense connectivity mechanism,which can avoid overfitting,obtain the local features effectively and prevent gradient vanishing even in limited training data.First,MSADCN designs multi-scale structures in the densely connected network to extract fine-grained features at different scales.Then,coordinate attention is embedded to focus on critical features and automatically locate the regions of interest(ROI)without additional annotation.In addition,to improve the model’s generalization,transfer learning is applied to train the proposed MSADCN on the public dataset IMDB-WIKI,and the obtained pre-trained weights are loaded onto the Radiological Society of North America(RSNA)dataset.Finally,label distribution learning(LDL)and expectation regression techniques are introduced into our model to exploit the correlation between hand bone images of different ages,which can obtain stable age estimates.Extensive experiments confirm that our model can converge more efficiently and obtain a mean absolute error(MAE)of 4.64 months,outperforming some state-of-the-art BAA methods.
基金Supported by the National Natural Science Foundation of China (61901308)。
文摘Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we propose a new generative adversarial network(GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention(SA) module with an implicit Laplacian offset attention(OA) module and to aggregate the adjacency features using a multiscale offset attention(MSOA)module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention(RMSOA) module, which utilizes multiscale structural relationships to generate finer details. Result The results of several experiments show that our method outperforms existing methods and is highly robust.
基金This work is supported by the National Natural Science Foundation of China(Grant No.61971057)MoE-CMCC Artifical Intelligence Project(No.MCM20190701).
文摘Time series data is a kind of data accumulated over time,which can describe the change of phenomenon.This kind of data reflects the degree of change of a certain thing or phenomenon.The existing technologies such as LSTM and ARIMA are better than convolutional neural network in time series prediction,but they are not enough to mine the periodicity of data.In this article,we perform periodic analysis on two types of time series data,select time metrics with high periodic characteristics,and propose a multi-scale prediction model based on the attention mechanism for the periodic trend of the data.A loss calculation method for traffic time series characteristics is proposed as well.Multiple experiments have been conducted on actual data sets.The experiments show that the method proposed in this paper has better performance than commonly used traffic prediction methods(ARIMA,LSTM,etc.)and 3%-5%increase on MAPE.
基金Supported by the National Natural Science Foundation of China(61903336,61976190)the Natural Science Foundation of Zhejiang Province(LY21F030015)。
文摘Background The use of remote photoplethysmography(rPPG)to estimate blood volume pulse in a noncontact manner has been an active research topic in recent years.Existing methods are primarily based on a singlescale region of interest(ROI).However,some noise signals that are not easily separated in a single-scale space can be easily separated in a multi-scale space.Also,existing spatiotemporal networks mainly focus on local spatiotemporal information and do not emphasize temporal information,which is crucial in pulse extraction problems,resulting in insufficient spatiotemporal feature modelling.Methods Here,we propose a multi-scale facial video pulse extraction network based on separable spatiotemporal convolution(SSTC)and dimension separable attention(DSAT).First,to solve the problem of a single-scale ROI,we constructed a multi-scale feature space for initial signal separation.Second,SSTC and DSAT were designed for efficient spatiotemporal correlation modeling,which increased the information interaction between the long-span time and space dimensions;this placed more emphasis on temporal features.Results The signal-to-noise ratio(SNR)of the proposed network reached 9.58dB on the PURE dataset and 6.77dB on the UBFC-rPPG dataset,outperforming state-of-the-art algorithms.Conclusions The results showed that fusing multi-scale signals yielded better results than methods based on only single-scale signals.The proposed SSTC and dimension-separable attention mechanism will contribute to more accurate pulse signal extraction.
基金The project is supported by the National Natural Science Foundation of China(52067013)the Key Projects of the Natural Science Foundation of Gansu Provincial Science and Technology Department(22JR5RA318).
文摘In light of the prevailing issue that the existing convolutional neural network(CNN)power quality disturbance identification method can only extract single-scale features,which leads to a lack of feature information and weak anti-noise performance,a new approach for identifying power quality disturbances based on an adaptive Kalman filter(KF)and multi-scale channel attention(MS-CAM)fused convolutional neural network is suggested.Single and composite-disruption signals are generated through simulation.The adaptive maximum likelihood Kalman filter is employed for noise reduction in the initial disturbance signal,and subsequent integration of multi-scale features into the conventional CNN architecture is conducted.The multi-scale features of the signal are captured by convolution kernels of different sizes so that the model can obtain diverse feature expressions.The attention mechanism(ATT)is introduced to adaptively allocate the extracted features,and the features are fused and selected to obtain the new main features.The Softmax classifier is employed for the classification of power quality disturbances.Finally,by comparing the recognition accuracy of the convolutional neural network(CNN),the model using the attention mechanism,the bidirectional long-term and short-term memory network(MS-Bi-LSTM),and the multi-scale convolutional neural network(MSCNN)with the attention mechanism with the proposed method.The simulation results demonstrate that the proposed method is higher than CNN,MS-Bi-LSTM,and MSCNN,and the overall recognition rate exceeds 99%,and the proposed method has significant classification accuracy and robust classification performance.This achievement provides a new perspective for further exploration in the field of power quality disturbance classification.
文摘With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.
基金Shenzhen Institute of Artificial Intelligence and Robotics for Society,Grant/Award Number:AC01202201003-02GuangDong Basic and Applied Basic Research Foundation,Grant/Award Number:2024A1515010252Longgang District Shenzhen's“Ten Action Plan”for Supporting Innovation Projects,Grant/Award Number:LGKCSDPT2024002。
文摘Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.
基金supported by the National Key Research&Development Program of China(grant no.2022YFC3500503)the National Natural Science Foundation of China(grant nos.62227807,12374171,12004034,62402041)+2 种基金the Beijing Institute of Technology Research Fund Program for Young Scholars,Chinathe Fundamental Research Funds for the Central Universities(grant nos.2024CX06060)Beijing Youth Talent Lifting Project.
文摘Due to their high mechanical compliance and excellent biocompatibility,conductive hydrogels exhibit significant potential for applications in flexible electronics.However,as the demand for high sensitivity,superior mechanical properties,and strong adhesion performance continues to grow,many conventional fabrication methods remain complex and costly.Herein,we propose a simple and efficient strategy to construct an entangled network hydrogel through a liquid-metal-induced cross-linking reaction,hydrogel demonstrates outstanding properties,including exceptional stretchability(1643%),high tensile strength(366.54 kPa),toughness(350.2 kJ m^(−3)),and relatively low mechanical hysteresis.The hydrogel exhibits long-term stable reusable adhesion(104 kPa),enabling conformal and stable adhesion to human skin.This capability allows it to effectively capture high-quality epidermal electrophysiological signals with high signal-to-noise ratio(25.2 dB)and low impedance(310 ohms).Furthermore,by integrating advanced machine learning algorithms,achieving an attention classification accuracy of 91.38%,which will significantly impact fields like education,healthcare,and artificial intelligence.
基金National Key Research and Development Program of China,Grant/Award Number:2018YFE0206900China Postdoctoral Science Foundation,Grant/Award Number:2023M731204+2 种基金The Open Project of Key Laboratory for Quality Evaluation of Ultrasound Surgical Equipment of National Medical Products Administration,Grant/Award Number:SMDTKL-2023-1-01The Hubei Province Key Research and Development Project,Grant/Award Number:2023BCB007CAAI-Huawei MindSpore Open Fund。
文摘Convolutional neural network(CNN)with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global feature.The transformer can extract the global information well but adapting it to small medical datasets is challenging and its computational complexity can be heavy.In this work,a serial and parallel network is proposed for the accurate 3D medical image segmentation by combining CNN and transformer and promoting feature interactions across various semantic levels.The core components of the proposed method include the cross window self-attention based transformer(CWST)and multi-scale local enhanced(MLE)modules.The CWST module enhances the global context understanding by partitioning 3D images into non-overlapping windows and calculating sparse global attention between windows.The MLE module selectively fuses features by computing the voxel attention between different branch features,and uses convolution to strengthen the dense local information.The experiments on the prostate,atrium,and pancreas MR/CT image datasets consistently demonstrate the advantage of the proposed method over six popular segmentation models in both qualitative evaluation and quantitative indexes such as dice similarity coefficient,Intersection over Union,95%Hausdorff distance and average symmetric surface distance.
基金supported by the National Natural Science Foundation of China(62272049,62236006,62172045)the Key Projects of Beijing Union University(ZKZD202301).
文摘In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.
基金Supported by the National Natural Science Foundation of China(61601176)。
文摘In this paper,we propose hierarchical attention dual network(DNet)for fine-grained image classification.The DNet can randomly select pairs of inputs from the dataset and compare the differences between them through hierarchical attention feature learning,which are used simultaneously to remove noise and retain salient features.In the loss function,it considers the losses of difference in paired images according to the intra-variance and inter-variance.In addition,we also collect the disaster scene dataset from remote sensing images and apply the proposed method to disaster scene classification,which contains complex scenes and multiple types of disasters.Compared to other methods,experimental results show that the DNet with hierarchical attention is robust to different datasets and performs better.
基金supported by the National Natural Science Foundation of China(No.62103298)。
文摘Aiming at the problems of low detection accuracy and large model size of existing object detection algorithms applied to complex road scenes,an improved you only look once version 8(YOLOv8)object detection algorithm for infrared images,F-YOLOv8,is proposed.First,a spatial-to-depth network replaces the traditional backbone network's strided convolution or pooling layer.At the same time,it combines with the channel attention mechanism so that the neural network focuses on the channels with large weight values to better extract low-resolution image feature information;then an improved feature pyramid network of lightweight bidirectional feature pyramid network(L-BiFPN)is proposed,which can efficiently fuse features of different scales.In addition,a loss function of insertion of union based on the minimum point distance(MPDIoU)is introduced for bounding box regression,which obtains faster convergence speed and more accurate regression results.Experimental results on the FLIR dataset show that the improved algorithm can accurately detect infrared road targets in real time with 3%and 2.2%enhancement in mean average precision at 50%IoU(mAP50)and mean average precision at 50%—95%IoU(mAP50-95),respectively,and 38.1%,37.3%and 16.9%reduction in the number of model parameters,the model weight,and floating-point operations per second(FLOPs),respectively.To further demonstrate the detection capability of the improved algorithm,it is tested on the public dataset PASCAL VOC,and the results show that F-YOLO has excellent generalized detection performance.
