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
作 者:赵蕾[1] 谢颖[1] ZHAO Lei;XIE Ying(Xi’an Institute of Translation,Xi’an 710105,China)
机构地区:[1]西安翻译学院
出 处:《自动化与仪器仪表》2019年第11期29-32,共4页Automation & Instrumentation
基 金:国家社会科学基金项目《我国学龄儿童(7-15岁)动作学习能力评级指标与发展常模研究》(No.17XTY007)
摘 要:针对传统图像标志点自动跟踪方法边缘轮廓特征模糊,导致跟踪性能受限的问题,提出体育运动图像序列标志点自动跟踪方法。由图像的几何不变矩与弱边缘特征量的几何分布,构建图像的分块模型,将待跟踪图像归入分块子空间,获取局部动态特征点检测输出,计算局部动态特征重建轮廓区域分布估计值,根据手工标注分块匹配样本图像,重建轮廓分布特征点,检测图像边缘轮廓特征。在此基础上,动态融合体育运动图像,获取边缘亮点模型约束项,结合RGB特征分解技术提取特征标志点特征。重构图像的三维信息特征,结合稳态匹配技术完成体育运动图像序列标志点自动跟踪。实验结果表明,采用该算法进行模糊体育运动图像的动态特征标志点自动跟踪处理,特征匹配精度高,自动跟踪性能较好,对动态特征标志点的定位精度较高。Aiming at the problem that the edge contour feature of traditional image marker point automatic tracking method is blurred,which leads to limited tracking performance,an automatic tracking method for sports image sequence marker points is proposed.From the geometric invariant moment of the image and the geometrical distribution of the weak edge feature quantity,the block model of the image is constructed,the image to be tracked is classified into the block subspace,the local dynamic feature point detection output is obtained,and the local dynamic feature reconstruction contour area distribution is calculated.The estimated value is based on manually labeling the block matching sample images,reconstructing the contour distribution feature points,and detecting the image edge contour features.On this basis,the sports image is dynamically integrated,and the edge bright point model constraint is obtained.The feature mark feature is extracted by combining RGB feature decomposition technology.The three-dimensional information features of the reconstructed image are combined with the steady-state matching technology to complete the automatic tracking of the sports image sequence marker points.The experimental results show that the algorithm is used to automatically track the dynamic feature points of fuzzy sports images.The feature matching accuracy is high,the automatic tracking performance is good,and the positioning accuracy of dynamic feature points is high.
分 类 号:TP399[自动化与计算机技术—计算机应用技术]
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:216.73.216.145