We try to give a quantitative and global discrimination function by studying mb/MS data using Fisher method that is a kind of pattern recognition methods. The reliability of the function is also analyzed. The results ...We try to give a quantitative and global discrimination function by studying mb/MS data using Fisher method that is a kind of pattern recognition methods. The reliability of the function is also analyzed. The results show that this criterion works well and has a global feature, which can be used as first-level filtering criterions in event identification. The quantitative and linear discrimination function makes it possible to identify events automatically and achieve the goal to react the events quickly and effectively.展开更多
目的显著性检测算法大多使用背景先验提高算法性能,但传统模型只是简单地将图像四周的边缘区域作为背景区域,导致结果在显著性物体触及到图像边界的情况下产生误检测。为更准确地应用背景先验,提出一种融合背景块再选取过程的显著性检...目的显著性检测算法大多使用背景先验提高算法性能,但传统模型只是简单地将图像四周的边缘区域作为背景区域,导致结果在显著性物体触及到图像边界的情况下产生误检测。为更准确地应用背景先验,提出一种融合背景块再选取过程的显著性检测方法。方法利用背景先验、中心先验和颜色分布特征获得种子向量并构建扩散矩阵,经扩散方法得到初步显著图,并以此为输入再经扩散方法得到二层显著图。依据Fisher准则的思想以二层显著图为基础创建背景块再选取过程,将选取的背景块组成背景向量并构建扩散矩阵,经扩散方法得到背景显著图。将背景显著图与二层显著图进行非线性融合获得最终显著图。结果在5个通用数据集上将本文算法与6种算法进行实验对比。本文算法在MSRA10K(Microsoft Research Asia 10K)数据集上,平均绝对误差(mean absolute error,MAE)取得了最小值,与基于多特征扩散方法的显著性物体检测算法(salient object detection via multi-feature diffusion-based method,LMH)相比,F值提升了0.84%,MAE降低了1.9%;在数据集ECSSD(extended complex scene saliency dataset)上,MAE取得了次优值,F值取得了最优值,与LMH算法相比,F值提升了1.33%;在SED2(segmentation evaluation database 2)数据集上,MAE与F值均取得了次优值,与LMH算法相比,F值提升了0.7%,MAE降低了0.93%。本文算法检测结果在主观对比中均优于LMH算法,表现为检测所得的显著性物体更加完整,置信度更高,在客观对比中,查全率均优于LMH算法。结论提出的显著性检测模型能更好地应用背景先验,使主客观检测结果有更好提升。展开更多
基金Contribution No.05FE3018,Institute of Geophysics,China Earthquake Administrstion
文摘We try to give a quantitative and global discrimination function by studying mb/MS data using Fisher method that is a kind of pattern recognition methods. The reliability of the function is also analyzed. The results show that this criterion works well and has a global feature, which can be used as first-level filtering criterions in event identification. The quantitative and linear discrimination function makes it possible to identify events automatically and achieve the goal to react the events quickly and effectively.
文摘目的显著性检测算法大多使用背景先验提高算法性能,但传统模型只是简单地将图像四周的边缘区域作为背景区域,导致结果在显著性物体触及到图像边界的情况下产生误检测。为更准确地应用背景先验,提出一种融合背景块再选取过程的显著性检测方法。方法利用背景先验、中心先验和颜色分布特征获得种子向量并构建扩散矩阵,经扩散方法得到初步显著图,并以此为输入再经扩散方法得到二层显著图。依据Fisher准则的思想以二层显著图为基础创建背景块再选取过程,将选取的背景块组成背景向量并构建扩散矩阵,经扩散方法得到背景显著图。将背景显著图与二层显著图进行非线性融合获得最终显著图。结果在5个通用数据集上将本文算法与6种算法进行实验对比。本文算法在MSRA10K(Microsoft Research Asia 10K)数据集上,平均绝对误差(mean absolute error,MAE)取得了最小值,与基于多特征扩散方法的显著性物体检测算法(salient object detection via multi-feature diffusion-based method,LMH)相比,F值提升了0.84%,MAE降低了1.9%;在数据集ECSSD(extended complex scene saliency dataset)上,MAE取得了次优值,F值取得了最优值,与LMH算法相比,F值提升了1.33%;在SED2(segmentation evaluation database 2)数据集上,MAE与F值均取得了次优值,与LMH算法相比,F值提升了0.7%,MAE降低了0.93%。本文算法检测结果在主观对比中均优于LMH算法,表现为检测所得的显著性物体更加完整,置信度更高,在客观对比中,查全率均优于LMH算法。结论提出的显著性检测模型能更好地应用背景先验,使主客观检测结果有更好提升。