检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
出 处:《计算机应用与软件》2008年第12期242-243,262,共3页Computer Applications and Software
摘 要:为改进角点检测算子的检测性能,提出了一种多尺度的Harris角点检测方法。该方法通过提取不同尺度下的角点,同时根据高斯核尺寸确定非极大值抑制窗口大小,然后根据角点响应函数值对每一尺度下检测出来的角点进行排序,且与前一小尺度下的角点进行比较,剔除伪角点,确保角点的精确定位。通过实验与几种角点检测方法检测结果相比,该方法检测角点的总误差小、错误率低,且匹配程度比原Harris算子显著提高,说明该方法是一种正确而有效的角点检测方法。To improve the performance of corner detector, a Muhi-scale Harris Corner Detection (~MHCD) method is presented. This method detects comers at different scales,and the size of the non-maximum suppression window is set according to the size of the Gaussian kernel. Consequently,the corners are ordered according to the value of comer response function, and the corner~ at current scale are compared with the corners at previous less scale so that false corners are removed to guarantee the best location for each comer point. Experiments show that the proposed method is of better performance such as less total errors, lower error rate, and higher match degree than some other corner detection methods. MHCD method is thereby proved to be a correct and efficient corner detection method.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.117