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:孔祥魁[1]
出 处:《计算机仿真》2016年第2期423-426,共4页Computer Simulation
摘 要:对运动图像特征中的某一关键点进行单独跟踪误差较大,主要是因为单关节点能提供的可识别特征较少,关节点特征也无法提供可用于跟踪的明显的方向、速度等参数变化规律特征,只能提供纹理特征,导致传统的跟踪算法无法根据少量纹理信息准确掌握图像序列中的运动方向参数变化规律特征,跟踪效果较差。提出双层特征优化算法的运动图像序列中关键关节点的跟踪优化方法。初始化运动图像序列中关键关节点和背景区域的直方图信息,对运动图像序列中的关键关节点进行分割,建立图像序列中关键关节点检测跟踪模型,对下一时刻关键关节点的大概方位进行预测,估计关键关节点的搜索区域,将像素灰度差作为图像序列匹配的距离准则,有效的完成运动图像序列中关键关节点的跟踪优化。仿真结果证明,提出的双层特征优化算法的运动图像序列中关键关节点的跟踪优化方法能有效的提高跟踪的精确度,有效地解决了运动图像序列中关键关节点难以跟踪的问题。Separate image characteristics of one of the key points of sports track has always been a difficult problem,mainly because of the single joint point can provide identifiable characteristics is less,the key points and cannot provide features can be used to track the obvious change law characteristic parameters,such as direction,speed,can only provide the texture feature,lead to the traditional tracking algorithm can't according to the small amount of texture information accurately control the direction of motion image sequence parameter variation characteristics of track effect is poorer. Based on double characteristics of the optimization algorithm of motion image sequence in the key joint point tracking optimization method. Initialization movement key key points in the image sequence and the background region histogram information,the motion image sequence segmentation,the key nodes of key joint point detection in image sequence tracking model is set up,the key key points about location of the next moment to estimate the joint point of the search area,the pixel gray difference as the distance image sequence matching criteria,effective complete movement key joint point of tracking in image sequence optimization. Experimental simulation results show that the proposed based on double characteristics of the optimization algorithm of motion image sequence in the key joint point of the track optimization method can effectively improve the accuracy of the tracking,effectively solve the key joint point is difficult to trace in motion image sequence problem.
分 类 号:TP391[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:216.73.216.229