根据尺度间小波系数的相关性和方差是双变量分布模型参数的理论,提出了应用基于上下文模型的空间自适应方法估计方差,并用双变量收缩法进行图像去噪的新方法.将新方法与仅使用待估计点与它的方形邻域窗来估计方差的双变量阈值去噪方法...根据尺度间小波系数的相关性和方差是双变量分布模型参数的理论,提出了应用基于上下文模型的空间自适应方法估计方差,并用双变量收缩法进行图像去噪的新方法.将新方法与仅使用待估计点与它的方形邻域窗来估计方差的双变量阈值去噪方法进行了比较.结果表明,用新方法去噪时图像的P SN R值与视觉效果都有提高和改善,新去噪方法具有理论上的一致性.展开更多
The airport apron scene contains rich contextual information about the spatial position relationship.Traditional object detectors only considered visual appearance and ignored the contextual information.In addition,th...The airport apron scene contains rich contextual information about the spatial position relationship.Traditional object detectors only considered visual appearance and ignored the contextual information.In addition,the detection accuracy of some categories in the apron dataset was low.Therefore,an improved object detection method using spatial-aware features in apron scenes called SA-FRCNN is presented.The method uses graph convolutional networks to capture the relative spatial relationship between objects in the apron scene,incorporating this spatial context into feature learning.Moreover,an attention mechanism is introduced into the feature extraction process,with the goal to focus on the spatial position and key features,and distance-IoU loss is used to achieve a more accurate regression.The experimental results show that the mean average precision of the apron object detection based on SAFRCNN can reach 95.75%,and the detection effect of some hard-to-detect categories has been significantly improved.The proposed method effectively improves the detection accuracy on the apron dataset,which has a leading advantage over other methods.展开更多
The main idea of pervasive computing is to make computing exist everywhere in the physical world.The smart home system is an important realisation of pervasive computing whose aim is to provide system users with an in...The main idea of pervasive computing is to make computing exist everywhere in the physical world.The smart home system is an important realisation of pervasive computing whose aim is to provide system users with an intelligent life experience.The key technique used to realise this is context awareness.Contexts in the living space can provide large amounts of information regarding users’behaviours and habits.Together with an information system,it can automatically execute many common operations of applications,instead of users,and can make the applications"smart".However,since contexts in the environment are diverse and sensitive,it is difficult to choose the ones that are most useful to the users’current activity.A proper scheduling strategy should first consider the users’demand.This paper proposes a context-aware scheduling algorithm that is based on correlation,with the purpose of improving the utilization rate of context collections.Experiments show that with the priority based on correlation in low-level contexts,the scheduling of reasoning tasks can reduce the cost of transmission.展开更多
文摘根据尺度间小波系数的相关性和方差是双变量分布模型参数的理论,提出了应用基于上下文模型的空间自适应方法估计方差,并用双变量收缩法进行图像去噪的新方法.将新方法与仅使用待估计点与它的方形邻域窗来估计方差的双变量阈值去噪方法进行了比较.结果表明,用新方法去噪时图像的P SN R值与视觉效果都有提高和改善,新去噪方法具有理论上的一致性.
基金supported by the Fundamental Research Funds for Central Universities of the Civil Aviation University of China(No.3122021088).
文摘The airport apron scene contains rich contextual information about the spatial position relationship.Traditional object detectors only considered visual appearance and ignored the contextual information.In addition,the detection accuracy of some categories in the apron dataset was low.Therefore,an improved object detection method using spatial-aware features in apron scenes called SA-FRCNN is presented.The method uses graph convolutional networks to capture the relative spatial relationship between objects in the apron scene,incorporating this spatial context into feature learning.Moreover,an attention mechanism is introduced into the feature extraction process,with the goal to focus on the spatial position and key features,and distance-IoU loss is used to achieve a more accurate regression.The experimental results show that the mean average precision of the apron object detection based on SAFRCNN can reach 95.75%,and the detection effect of some hard-to-detect categories has been significantly improved.The proposed method effectively improves the detection accuracy on the apron dataset,which has a leading advantage over other methods.
基金partially supported by the National Natural Science Foundation of China under Grant No.61103115the Hunan Provincial Natural Science Foundation of China under Grant No.11JJ4058the Scientific Research Fund of Hunan Provincial Education Department under Grant No.11A041
文摘The main idea of pervasive computing is to make computing exist everywhere in the physical world.The smart home system is an important realisation of pervasive computing whose aim is to provide system users with an intelligent life experience.The key technique used to realise this is context awareness.Contexts in the living space can provide large amounts of information regarding users’behaviours and habits.Together with an information system,it can automatically execute many common operations of applications,instead of users,and can make the applications"smart".However,since contexts in the environment are diverse and sensitive,it is difficult to choose the ones that are most useful to the users’current activity.A proper scheduling strategy should first consider the users’demand.This paper proposes a context-aware scheduling algorithm that is based on correlation,with the purpose of improving the utilization rate of context collections.Experiments show that with the priority based on correlation in low-level contexts,the scheduling of reasoning tasks can reduce the cost of transmission.
