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:王世伟[1,2]
机构地区:[1]北京体育大学研究生院,北京100084 [2]成都体育学院,四川成都610041
出 处:《计算机仿真》2016年第12期216-219,共4页Computer Simulation
摘 要:由于排球运动员视频中的姿势具有动态变化特征,使得目标特征多样,变化频繁。传统的对排球运动员视频姿势目标定位方法,主要通过视频中运动员的运动特征进行定位,忽略了姿势的频繁变化对特征的影响,导致姿势目标定位误差大,效率低的问题。提出基于背景差理论的排球运动员视频中姿势目标定位优化方法。先融合于背景差理论获取姿势目标区域位置,组建排球运动员视频中姿势目标的颜色直方图和梯度方向直方图,将颜色和梯度方向直方图相融合,初始化姿势目标位置,计算出姿势目标区域特征权值,得到排球运动员视频中多帧姿势目标和背景的特征分量,获取近似度函数,进行姿势且标的匹配,利用匹配的结果完成排球运动员视频中姿势目标优化定位。实验结果表明,所提方法能够有效提升排球运动员视频中姿势目标定位准确度。A target location method of volleyball athlete posture in video based on the background subtraction theory is proposed. Firstly, the method the target region position of posture integrated with the background subtraction theory is obtained, and the color histogram and gradient direction histogram of athlete posture target in the video are built. Then, the color histogram is integrated with the gradient direction histogram, and the location of posture target is initialized. Moreover, the feature weight of posture target region is worked out, and the characteristic component of athlete multi -frame posture target and background in video is obtained to acquire the approximation ratio function. Finally, the matching of posture target is achieved, and the matching result is used to complete the target optimization location of volleyball athlete posture in video. The simulation results show that the method mentioned above can improve the target location accuracy of volleyball athlete posture in the video.
分 类 号:TP391.41[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