Detecting pavement cracks is critical for road safety and infrastructure management.Traditional methods,relying on manual inspection and basic image processing,are time-consuming and prone to errors.Recent deep-learni...Detecting pavement cracks is critical for road safety and infrastructure management.Traditional methods,relying on manual inspection and basic image processing,are time-consuming and prone to errors.Recent deep-learning(DL)methods automate crack detection,but many still struggle with variable crack patterns and environmental conditions.This study aims to address these limitations by introducing the Masker Transformer,a novel hybrid deep learning model that integrates the precise localization capabilities of Mask Region-based Convolutional Neural Network(Mask R-CNN)with the global contextual awareness of Vision Transformer(ViT).The research focuses on leveraging the strengths of both architectures to enhance segmentation accuracy and adaptability across different pavement conditions.We evaluated the performance of theMaskerTransformer against other state-of-theartmodels such asU-Net,TransformerU-Net(TransUNet),U-NetTransformer(UNETr),SwinU-NetTransformer(Swin-UNETr),You Only Look Once version 8(YoloV8),and Mask R-CNN using two benchmark datasets:Crack500 and DeepCrack.The findings reveal that the MaskerTransformer significantly outperforms the existing models,achieving the highest Dice SimilarityCoefficient(DSC),precision,recall,and F1-Score across both datasets.Specifically,the model attained a DSC of 80.04%on Crack500 and 91.37%on DeepCrack,demonstrating superior segmentation accuracy and reliability.The high precision and recall rates further substantiate its effectiveness in real-world applications,suggesting that the Masker Transformer can serve as a robust tool for automated pavement crack detection,potentially replacing more traditional methods.展开更多
提出一种基于多任务注意力机制的无参考屏幕内容图像质量评价算法(multi-task attention mechanism based no reference quality assessment algorithm for screen content images,MTA-SCI)。MTA-SCI首先使用自注意力机制提取屏幕内容...提出一种基于多任务注意力机制的无参考屏幕内容图像质量评价算法(multi-task attention mechanism based no reference quality assessment algorithm for screen content images,MTA-SCI)。MTA-SCI首先使用自注意力机制提取屏幕内容图像的全局特征,增强对屏幕内容图像整体信息的表征能力;然后使用综合局部注意力机制提取屏幕内容图像的局部特征,使局部特征能够聚焦于屏幕内容图像中更吸引人注意的细节部分;最后使用双通道特征映射模块预测屏幕内容图像的质量分数。在SCID和SIQAD数据集上,MTA-SCI的斯皮尔曼秩序相关系数(Spearman's rank order correlation coefficient,SRCC)分别达到0.9602和0.9233,皮尔森线性相关系数(Pearson linear correlation coefficient,PLCC)分别达到0.9609和0.9294。实验结果表明,MTA-SCI在预测屏幕内容图像质量任务中具有较高的准确性。展开更多
To fully leverage the advantages of mechanization and informatization in tunnel boring machine(TBM)operations,the authors aim to promote the advancement of tunnel construction technology toward intelligent development...To fully leverage the advantages of mechanization and informatization in tunnel boring machine(TBM)operations,the authors aim to promote the advancement of tunnel construction technology toward intelligent development.This involved exploring the deep integration of next-generation artificial intelligence technologies,such as sensing technology,automatic control technology,big data technology,deep learning,and machine vision,with key operational processes,including TBM excavation,direction adjustment,step changes,inverted arch block assembly,material transportation,and operation status assurance.The results of this integration are summarized as follows.(1)TBM key excavation parameter prediction algorithm was developed with an accuracy rate exceeding 90%.The TBM intelligent step-change control algorithm,based on machine vision,achieved an image segmentation accuracy rate of 95%and gripper shoe positioning error of±5 mm.(2)An automatic positioning system for inverted arch blocks was developed,enabling real-time perception of the spatial position and deviation during the assembly process.The system maintains an elevation positioning deviation within±3 mm and a horizontal positioning deviation within±10 mm,reducing the number of surveyors in each work team.(3)A TBM intelligent rail transportation system that achieves real-time human-machine positioning,automatic switch opening and closing,automatic obstacle avoidance,intelligent transportation planning,and integrated scheduling and command was designed.Each locomotive formation reduces one shunter and improves comprehensive transportation efficiency by more than 20%.(4)Intelligent analysis and prediction algorithms were developed to monitor and predict the trends of the hydraulic and gear oil parameters in real time,enhancing the proactive maintenance and system reliability.展开更多
文摘Detecting pavement cracks is critical for road safety and infrastructure management.Traditional methods,relying on manual inspection and basic image processing,are time-consuming and prone to errors.Recent deep-learning(DL)methods automate crack detection,but many still struggle with variable crack patterns and environmental conditions.This study aims to address these limitations by introducing the Masker Transformer,a novel hybrid deep learning model that integrates the precise localization capabilities of Mask Region-based Convolutional Neural Network(Mask R-CNN)with the global contextual awareness of Vision Transformer(ViT).The research focuses on leveraging the strengths of both architectures to enhance segmentation accuracy and adaptability across different pavement conditions.We evaluated the performance of theMaskerTransformer against other state-of-theartmodels such asU-Net,TransformerU-Net(TransUNet),U-NetTransformer(UNETr),SwinU-NetTransformer(Swin-UNETr),You Only Look Once version 8(YoloV8),and Mask R-CNN using two benchmark datasets:Crack500 and DeepCrack.The findings reveal that the MaskerTransformer significantly outperforms the existing models,achieving the highest Dice SimilarityCoefficient(DSC),precision,recall,and F1-Score across both datasets.Specifically,the model attained a DSC of 80.04%on Crack500 and 91.37%on DeepCrack,demonstrating superior segmentation accuracy and reliability.The high precision and recall rates further substantiate its effectiveness in real-world applications,suggesting that the Masker Transformer can serve as a robust tool for automated pavement crack detection,potentially replacing more traditional methods.
文摘提出一种基于多任务注意力机制的无参考屏幕内容图像质量评价算法(multi-task attention mechanism based no reference quality assessment algorithm for screen content images,MTA-SCI)。MTA-SCI首先使用自注意力机制提取屏幕内容图像的全局特征,增强对屏幕内容图像整体信息的表征能力;然后使用综合局部注意力机制提取屏幕内容图像的局部特征,使局部特征能够聚焦于屏幕内容图像中更吸引人注意的细节部分;最后使用双通道特征映射模块预测屏幕内容图像的质量分数。在SCID和SIQAD数据集上,MTA-SCI的斯皮尔曼秩序相关系数(Spearman's rank order correlation coefficient,SRCC)分别达到0.9602和0.9233,皮尔森线性相关系数(Pearson linear correlation coefficient,PLCC)分别达到0.9609和0.9294。实验结果表明,MTA-SCI在预测屏幕内容图像质量任务中具有较高的准确性。
文摘To fully leverage the advantages of mechanization and informatization in tunnel boring machine(TBM)operations,the authors aim to promote the advancement of tunnel construction technology toward intelligent development.This involved exploring the deep integration of next-generation artificial intelligence technologies,such as sensing technology,automatic control technology,big data technology,deep learning,and machine vision,with key operational processes,including TBM excavation,direction adjustment,step changes,inverted arch block assembly,material transportation,and operation status assurance.The results of this integration are summarized as follows.(1)TBM key excavation parameter prediction algorithm was developed with an accuracy rate exceeding 90%.The TBM intelligent step-change control algorithm,based on machine vision,achieved an image segmentation accuracy rate of 95%and gripper shoe positioning error of±5 mm.(2)An automatic positioning system for inverted arch blocks was developed,enabling real-time perception of the spatial position and deviation during the assembly process.The system maintains an elevation positioning deviation within±3 mm and a horizontal positioning deviation within±10 mm,reducing the number of surveyors in each work team.(3)A TBM intelligent rail transportation system that achieves real-time human-machine positioning,automatic switch opening and closing,automatic obstacle avoidance,intelligent transportation planning,and integrated scheduling and command was designed.Each locomotive formation reduces one shunter and improves comprehensive transportation efficiency by more than 20%.(4)Intelligent analysis and prediction algorithms were developed to monitor and predict the trends of the hydraulic and gear oil parameters in real time,enhancing the proactive maintenance and system reliability.
