In recent years,deep learning has been introduced into the field of Single-pixel imaging(SPI),garnering significant attention.However,conventional networks still exhibit limitations in preserving image details.To addr...In recent years,deep learning has been introduced into the field of Single-pixel imaging(SPI),garnering significant attention.However,conventional networks still exhibit limitations in preserving image details.To address this issue,we integrate Large Kernel Convolution(LKconv)into the U-Net framework,proposing an enhanced network structure named U-LKconv network,which significantly enhances the capability to recover image details even under low sampling conditions.展开更多
Graph convolutional networks(GCNs)have become a dominant approach for skeleton-based action recognition tasks.Although GCNs have made significant progress in modeling skeletons as spatial-temporal graphs,they often re...Graph convolutional networks(GCNs)have become a dominant approach for skeleton-based action recognition tasks.Although GCNs have made significant progress in modeling skeletons as spatial-temporal graphs,they often require stacking multiple graph convolution layers to effectively capture long-distance relationships among nodes.This stacking not only increases computational burdens but also raises the risk of over-smoothing,which can lead to the neglect of crucial local action features.To address this issue,we propose a novel multi-scale adaptive large kernel graph convolutional network(MSLK-GCN)to effectively aggregate local and global spatio-temporal correlations while maintaining the computational efficiency.The core components of the network include two multi-scale large kernel graph convolution(LKGC)modules,a multi-channel adaptive graph convolution(MAGC)module,and a multi-scale temporal self-attention convolution(MSTC)module.The LKGC module adaptively focuses on active motion regions by utilizing a large convolution kernel and a gating mechanism,effectively capturing long-distance dependencies within the skeleton sequence.Meanwhile,the MAGC module dynamically learns relationships between different joints by adjusting connection weights between nodes.To further enhance the ability to capture temporal dynamics,the MSTC module effectively aggregates the temporal information by integrating Efficient Channel Attention(ECA)with multi-scale convolution.In addition,we use a multi-stream fusion strategy to make full use of different modal skeleton data,including bone,joint,joint motion,and bone motion.Exhaustive experiments on three scale-varying datasets,i.e.,NTU-60,NTU-120,and NW-UCLA,demonstrate that our MSLK-GCN can achieve state-of-the-art performance with fewer parameters.展开更多
This paper suggests an improved you only look once version 8n(YOLOv8n)algorithm for apple leaf disease detection,abbreviated as ALWB-YOLOv8n.The model is comprised of four essential components.Initially,arbitrary kern...This paper suggests an improved you only look once version 8n(YOLOv8n)algorithm for apple leaf disease detection,abbreviated as ALWB-YOLOv8n.The model is comprised of four essential components.Initially,arbitrary kernel convolution(AKConv)replaces the convolution module,which significantly decreases both the model’s parameter count and its overall size.Secondly,the large selective kernel network(LSKNet)attention mechanism is added in the Backbone,which can dynamically adjust the spatial sensory domain,and experiments have proved that this method is extremely advantageous for small target detection.Third,a weighted bi-directional feature pyramid network is introduced,which enables the model to achieve multi-scale feature fusion and is more concise and faster.Finally,wise intersection over union(WIoU)is used to replace complete intersection over union(CIoU)in YOLOv8,and the idea of focal loss is introduced,which effectively solves the detection problems in cases such as apple leaves occluding each other and blurred boundaries of diseased leaves.The improved algorithm exhibits superior performance compared to other common object detection algorithms.Compared with YOLOv8n,the improved algorithm achieves 2.3%improvement in precision,3.8%improvement in recall,and 2.5%and 2.7%improvement in mAP0.5 and mAP0.5:0.95,respectively.Compared with YOLOv8n,the improved model reduces the number of parameters and size of the model and realizes real-time monitoring with a frames per second(FPS)of 50.5.展开更多
Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of cr...Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of crack detection in cement pavement improves,the depth and width of the network structure are significantly increased,which necessitates more computing power and storage space.This limitation hampers the practical implementation of crack detection models on various platforms,particularly portable devices like small mobile devices.To solve these problems,we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature information and combines cross-fusion modules and coordinated attention mechanisms formore efficient feature fusion.Firstly,we use small channel convolution to construct shallow feature extractionmodule(SFEM)to extract low-level feature information of cracks in cement pavement images,in order to obtainmore information about cracks in the shallowfeatures of images.In addition,we construct large kernel atrous convolution(LKAC)to enhance crack information,which incorporates coordination attention mechanism for non-crack information filtering,and large kernel atrous convolution with different cores,using different receptive fields to extract more detailed edge and context information.Finally,the three-stage feature map outputs from the shallow feature extraction module is cross-fused with the two-stage feature map outputs from the large kernel atrous convolution module,and the shallow feature and detailed edge feature are fully fused to obtain the final crack prediction map.We evaluate our method on three public crack datasets:DeepCrack,CFD,and Crack500.Experimental results on theDeepCrack dataset demonstrate the effectiveness of our proposed method compared to state-of-the-art crack detection methods,which achieves Precision(P)87.2%,Recall(R)87.7%,and F-score(F1)87.4%.Thanks to our lightweight crack detectionmodel,the parameter count of the model in real-world detection scenarios has been significantly reduced to less than 2M.This advancement also facilitates technical support for portable scene detection.展开更多
摘要In recent years,deep learning has been introduced into the field of Single-pixel imaging(SPI),garnering significant attention.However,conventional networks still exhibit limitations in preserving image details.To address this issue,we integrate Large Kernel Convolution(LKconv)into the U-Net framework,proposing an enhanced network structure named U-LKconv network,which significantly enhances the capability to recover image details even under low sampling conditions.
基金supported in part by the National Natural Science Foundation of China under Grant No.61976127the Shandong Provincial Natural Science Foundation under Grant No.ZR2024MF030+1 种基金the Taishan Scholar Program of Shandong Province of China under Grant No.tsqn202306150the Key Research and Development Program of Shandong Province of China under Grant No.2025CXPT096.
摘要Graph convolutional networks(GCNs)have become a dominant approach for skeleton-based action recognition tasks.Although GCNs have made significant progress in modeling skeletons as spatial-temporal graphs,they often require stacking multiple graph convolution layers to effectively capture long-distance relationships among nodes.This stacking not only increases computational burdens but also raises the risk of over-smoothing,which can lead to the neglect of crucial local action features.To address this issue,we propose a novel multi-scale adaptive large kernel graph convolutional network(MSLK-GCN)to effectively aggregate local and global spatio-temporal correlations while maintaining the computational efficiency.The core components of the network include two multi-scale large kernel graph convolution(LKGC)modules,a multi-channel adaptive graph convolution(MAGC)module,and a multi-scale temporal self-attention convolution(MSTC)module.The LKGC module adaptively focuses on active motion regions by utilizing a large convolution kernel and a gating mechanism,effectively capturing long-distance dependencies within the skeleton sequence.Meanwhile,the MAGC module dynamically learns relationships between different joints by adjusting connection weights between nodes.To further enhance the ability to capture temporal dynamics,the MSTC module effectively aggregates the temporal information by integrating Efficient Channel Attention(ECA)with multi-scale convolution.In addition,we use a multi-stream fusion strategy to make full use of different modal skeleton data,including bone,joint,joint motion,and bone motion.Exhaustive experiments on three scale-varying datasets,i.e.,NTU-60,NTU-120,and NW-UCLA,demonstrate that our MSLK-GCN can achieve state-of-the-art performance with fewer parameters.
基金supported by the Intelligent Identification and Early Warning System for Pests and Diseases in Small-seeded Rapeseed(No.24ZYCGSN01360)the Intelligent Management Platform for Vegetable Greenhouses Project(No.YH003001)+1 种基金the Intelligent Agricultural Breeding System Project(No.YH003002)the Research and Application of AIoT Based Big Data System for Apple Tree Pest and Disease Detection(No.2024WA013)。
摘要This paper suggests an improved you only look once version 8n(YOLOv8n)algorithm for apple leaf disease detection,abbreviated as ALWB-YOLOv8n.The model is comprised of four essential components.Initially,arbitrary kernel convolution(AKConv)replaces the convolution module,which significantly decreases both the model’s parameter count and its overall size.Secondly,the large selective kernel network(LSKNet)attention mechanism is added in the Backbone,which can dynamically adjust the spatial sensory domain,and experiments have proved that this method is extremely advantageous for small target detection.Third,a weighted bi-directional feature pyramid network is introduced,which enables the model to achieve multi-scale feature fusion and is more concise and faster.Finally,wise intersection over union(WIoU)is used to replace complete intersection over union(CIoU)in YOLOv8,and the idea of focal loss is introduced,which effectively solves the detection problems in cases such as apple leaves occluding each other and blurred boundaries of diseased leaves.The improved algorithm exhibits superior performance compared to other common object detection algorithms.Compared with YOLOv8n,the improved algorithm achieves 2.3%improvement in precision,3.8%improvement in recall,and 2.5%and 2.7%improvement in mAP0.5 and mAP0.5:0.95,respectively.Compared with YOLOv8n,the improved model reduces the number of parameters and size of the model and realizes real-time monitoring with a frames per second(FPS)of 50.5.
基金supported by the National Natural Science Foundation of China(No.62176034)the Science and Technology Research Program of Chongqing Municipal Education Commission(No.KJZD-M202300604)the Natural Science Foundation of Chongqing(Nos.cstc2021jcyj-msxmX0518,2023NSCQ-MSX1781).
摘要Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of crack detection in cement pavement improves,the depth and width of the network structure are significantly increased,which necessitates more computing power and storage space.This limitation hampers the practical implementation of crack detection models on various platforms,particularly portable devices like small mobile devices.To solve these problems,we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature information and combines cross-fusion modules and coordinated attention mechanisms formore efficient feature fusion.Firstly,we use small channel convolution to construct shallow feature extractionmodule(SFEM)to extract low-level feature information of cracks in cement pavement images,in order to obtainmore information about cracks in the shallowfeatures of images.In addition,we construct large kernel atrous convolution(LKAC)to enhance crack information,which incorporates coordination attention mechanism for non-crack information filtering,and large kernel atrous convolution with different cores,using different receptive fields to extract more detailed edge and context information.Finally,the three-stage feature map outputs from the shallow feature extraction module is cross-fused with the two-stage feature map outputs from the large kernel atrous convolution module,and the shallow feature and detailed edge feature are fully fused to obtain the final crack prediction map.We evaluate our method on three public crack datasets:DeepCrack,CFD,and Crack500.Experimental results on theDeepCrack dataset demonstrate the effectiveness of our proposed method compared to state-of-the-art crack detection methods,which achieves Precision(P)87.2%,Recall(R)87.7%,and F-score(F1)87.4%.Thanks to our lightweight crack detectionmodel,the parameter count of the model in real-world detection scenarios has been significantly reduced to less than 2M.This advancement also facilitates technical support for portable scene detection.