首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到18条相似文献,搜索用时 125 毫秒
1.
为能有效检索当前大量的三维人体运动捕获数据从而投入使用,针对三维人体运动捕获数据的独有特性,提出一种高效的检索方法。首先通过关键帧提取对原始运动数据降维,然后采用自定义的符合人体运动语义的特征将原始角度数据转换为特征序列。根据数据库中所有运动片段对应的特征序列构建一种基于姿态特征的索引空间。检索时通过在索引空间上顺序匹配姿态特征来查找时序一致的匹配运动片段。实验结果表明,与大多数现有方法相比,该方法由于较好的运动语义特征提取,因此具有更好的时间效率,更高的灵活性和检索精度,能够满足多种运动数据的检索需要。  相似文献   

2.
基于关键帧的三维人体运动检索   总被引:4,自引:1,他引:3  
提出一种基于关键帧的三维人体运动检索技术.首先采用骨骼夹角作为对原始运动数据的特征表示并提取运动片断关键帧集合,以此作为原始运动片断的特征表示;然后基于所提取关键帧数据在相似运动片断之间具有一致性的特点,在两两关键帧集合之间建立距离矩阵进行相似度匹配.实验结果表明,与现有大多数基于内容的三维人体运动数据检索方法相比,该方法能够取得更好的时间效率且不依赖于任何预先设定的参数,相对于现有基于关键帧的运动检索技术而言,其能够获得更好的检索效果.  相似文献   

3.
运动相似性度量是基于运动图的人体运动合成技术的关键.现有方法主要使用运动捕捉数据姿态数值特征进行相似性度量与合成控制,很难处理语义描述上同类型运动数据集中的不同运动实现版本间的时间与空间特征分布变化的问题.提出了引入用户语义控制来改进基于运动图的人体运动合成方法.使用关系特征作为高层语义描述,刻画同类型运动的空间变化特征;通过自学习过程,获得运动类模板,作为同类型运动的空-时特征语义描述;通过将运动类模板数据与人体运动序列文件进行匹配,实现运动类型识别和自动语义信息标注;借助关系特征语义描述及运动序列文件的语义标注信息,实现在基于运动图的运动合成中引入用户直观的高层语义控制.运动合成实验结果显示了该方法的有效性,为获得高质量人体运动合成数据提供途径.  相似文献   

4.
三维人体运动特征可视化与交互式运动分割   总被引:3,自引:0,他引:3  
肖俊  庄越挺  吴飞 《软件学报》2008,19(8):1995-2003
为了从运动序列中提取不同类型的运动片段进行人体动画创作,提出一种三维人体运动数据可视化与交互式分割技术.首先,采用人体各主要骨骼夹角作为对原始运动数据的几何特征表示,并提出一种启发式方法自动检测其潜在分割点,最后将提取的运动特征可视化并使用可交互用户界面对其进行精确分割.实验结果表明。该特征表示及交互式分割方法能够更加方便、准确、高效地对包含多种类型的长序列三维人体运动数据进行分割.  相似文献   

5.
提出了一种基于正弦级数拟合的行为识别方法.该方法利用二值轮廓序列来表示给定的运动图像序列,按照时针顺序计算从轮廓质心到轮廓边界点的距离,将人体轮廓转化为距离曲线,并将这一距离曲线利用正弦级数进行拟合,将距离曲线转化为正弦参数,从而极大地减小了计算量,将行为识别过程转化为曲线参数特征匹配的过程.在特征匹配过程中,通过计算待预测行为与已知类别行为的特征级数距离,对待预测行为中的每一个动作进行分类,最后通过投票决定该行为所属类别.在包含90个不同运动类别的视频数据库上进行留一交叉验证,实验结果表明,提出的方法能够有效地进行人体行为识别.  相似文献   

6.
多变量时间序列模式挖掘的研究   总被引:4,自引:0,他引:4  
张军  吴绍春  王炜 《计算机工程与设计》2006,27(18):3364-3366,3384
多变量时间序列数据集合在许多领域中存在,由于其观测变量之间的相互关联性,往往需要进行综合分析.使用基于时间序列相似性的多变量时间序列模式挖掘方法,从历史数据中寻找出相似的多变量时间序列.将多变量的数据集分段平均为连续矩阵,并采用基于主成分分析和奇异值分解的方法来对矩阵进行相似性比较,最后通过相邻片断的合并以组成更高层次的时序片断,以提高模式的匹配的范围.并在地震前兆数据进行了实现.  相似文献   

7.
人体运动路径的编辑算法   总被引:1,自引:0,他引:1  
对现有的路径编辑方法进行了较大改进,将运动自动简化技术引入到传统的时空优化方法中,同时将物理约束引入到传统的路径变换方法,保证了优化过程的快速收敛和结果运动的物理真实性.算法框架包括模型简化、运动简化、路径编辑、运动合成和运动复原等5个部分.实验结果表明,该算法能够将人体运动从原始路径上成功地映射到新路径上.  相似文献   

8.
提出基于概率主成分分析的三维人体运动自动识别与分类算法.它根据不同类别的人体运动应各有自己代表性的特征集,采用概率PCA方法建立各类动作的高斯分布模型;然后构建基于最小错误率贝叶斯决策理论的多分类器,实现对未知的动作序列(或具有代表性的帧)进行多分类决策.该方法具有概率模型的优点,适合高维数据处理;同时,这种方法能够提取运动数据的内在特征,较好地消除了运动数据在时间轴上的差异带来的问题,从而准确地对运动数据进行分类,实验结果证明了本文方法的有效性.  相似文献   

9.
针对人体运动的复杂性和噪声干扰的无序性,提出一种基于运动分割和稀疏低秩分解的失真人体运动捕捉数据恢复方法.首先利用双边滤波对失真运动数据进行预修正,降低干扰数据的奇异信息并保证运动序列的连贯性;其次采用概率主元分析方法将修正后的运动数据进行语义行为自动分割,得到不同姿态的运动语义子区间;再利用加速近端梯度优化算法对每个失真运动子片段数据矩阵根据其更优低秩特性进行稀疏低秩分解,实现运动子片段数据的局部恢复;最后将局部恢复后的各子运动片段根据人体运动序列的时序特性组合,达到整体失真运动捕捉数据恢复的目的.实验结果表明,该方法能够有效地对失真人体运动数据进行恢复,效果显著,有助于重构逼近真实人体姿态的运动捕捉数据.  相似文献   

10.
近年来,人体下肢关节点定位成为了人体运动跟踪与分析中一个重要研究课题。提出了一种下肢关节点自动定位方法,从无关节标记的人体运动图像序列中定位下肢关节点。该方法首先采用背景剪除技术从图像序列中分割人体目标对象,并建立人体下肢骨架模型。然后,利用关节角度预测方法估计膝踝关节点的位置,在基于下肢外观模型的匹配计算基础上获得下肢关节点的真实位置。实验结果表明,该方法简单有效,下肢关节点定位结果令人满意。  相似文献   

11.
This paper makes use of both feature points and silhouettes to deliver fast 3D shape recovery. The algorithm exploits object silhouettes in two views to establish a 3D rim curve, which is defined with respect to the two frontier points arising from two views. The images of this 3D rim curve in the two views are matched using cross-correlation technique. A 3D planar rim curve is then reconstructed using point-based reconstruction method. A set of 3D rim curves enclosing the object can be obtained from an image sequence captured under circular motion. Silhouettes are further utilized to check for mismatched rim points. The proposed method solves the problem of reconstruction of concave object surface, which is usually left unresolved in general silhouette-based reconstruction methods. In addition, the property of the reconstructed 3D rim curves allows fast surface extraction. Experimental results with real data are presented.  相似文献   

12.
数字化三维蹦床运动模拟与仿真系统——VHTramPoline   总被引:4,自引:0,他引:4  
王兆其  夏时洪  邱显杰  魏毅  刘莉  黄河 《计算机学报》2007,30(3):498-504,F0003
设计和实现了一个用于辅助蹦床运动科学训练的计算机模拟与仿真软件系统VHTrampoline.其原理是:在人体运动生物力学数据和真实人体运动捕获数据的基础上,通过运动编辑技术实现技术动作的修改和成套技术动作的模拟,并用人体运动方程分析和验证模拟结果;同时,基于虚拟现实方法将模拟结果与真实视频同步对比实现可视化的分析.除了必须的交互操作,文中涉及到的计算都是实时的.与传统训练方法相比,该系统具有直观、量化等优点.  相似文献   

13.
一种虚拟人导航运动的路径规划算法   总被引:2,自引:0,他引:2  
提出了一种虚拟人在复杂的3D障碍环境中根据导航目标快速进行最优路径规划的算法,该算法以使用栅格法表示虚拟环境为基础。首先,将虚拟环境中虚拟人高度范围内所有障碍物的几何形状映射到一个离散的2D位图,并对障碍物进行"膨胀";然后,使用提出的算法规划出一条从初始位置到目标位置的最优路径,引导虚拟人在虚拟环境中进行导航运动。该方法可以在较少的内存代价和计算代价的情况下,快速规划出从虚拟人目前位置到目标位置的最优路径,算法的可行性和有效性经过实验验证。  相似文献   

14.
Classification of the Dubins set   总被引:1,自引:0,他引:1  
Given two points in a plane, each with a prescribed direction of motion in it, the question being asked is to find the shortest smooth path of bounded curvature that joins them. The classical 1957 result by Dubins gives a sufficient set of paths (each consisting of circular arcs and straight line segments) which always contains the shortest path. The latter is then found by explicitly computing all paths on the list and then comparing them. This may become a problem in applications where computation time is critical, such as in real-time robot motion planning. Instead, the logical classification scheme considered in this work allows one to extract the shortest path from the Dubins set directly, without explicitly calculating the candidate paths. The approach is demonstrated on one of two possible cases that appear here — when the distance between the two points is relatively large (the case with short distances can be treated similarly). Besides computational savings, this result sheds light on the nature of factors affecting the length of paths in the Dubins problem, and is useful for further extensions, e.g. for finding the shortest path between a point and a manifold in the corresponding configuration space.  相似文献   

15.
Animated virtual human characters are a common feature in interactive graphical applications, such as computer and video games, online virtual worlds and simulations. Due to dynamic nature of such applications, character animation must be responsive and controllable in addition to looking as realistic and natural as possible. Though procedural and physics-based animation provide a great amount of control over motion, they still look too unnatural to be of use in all but a few specific scenarios, which is why interactive applications nowadays still rely mainly on recorded and hand-crafted motion clips. The challenge faced by animation system designers is to dynamically synthesize new, controllable motion by concatenating short motion segments into sequences of different actions or by parametrically blending clips that correspond to different variants of the same logical action. In this article, we provide an overview of research in the field of example-based motion synthesis for interactive applications. We present methods for automated creation of supporting data structures for motion synthesis and describe how they can be employed at run-time to generate motion that accurately accomplishes tasks specified by the AI or human user.  相似文献   

16.
针对无人艇运动规划问题,通过Dubins路径的理论分析,提出一种利用纯粹几何方法的Dubins路径计算方法。该方法中没有出现解方程组的运算,而是首先根据无人艇运动状态计算转向圆,然后利用几何方法计算转向圆间的公切线,最后通过公切线连接得到Dubins路径。通过5组仿真实验验证了所提方法的有效性。前4组仿真实验分别设计了计算Dubins路径过程中可能出现的各种情形,以验证算法适用于多种情况的Dubins路径计算。最后一组仿真实验用于无人艇的路径规划及运动状态调整,仿真结果表明,基于Dubins路径的无人艇运动规划算法是可行的。  相似文献   

17.
In a manufacturing environment where a redundant manipulator is programmed to follow a specific trajectory such as welding, painting, and soldering, it is often the case that the manipulator reaches a singular configuration where the program is stopped, the manipulator has to be switched to a new configuration, and the motion continued. This paper presents a method of determining the initial configuration of robotic manipulators to traverse a path trajectory without halting the motion. The method consists of: (1) identifying singular curves/surfaces using the Jacobian rank deficiency method; (2) determining non-crossable curves/surfaces using acceleration-based crossability criteria; (3) finding if the path intersects any non-crossable singular curve/surface. If there is not any intersection, the manipulator does not interrupt with any initial configuration on the trajectory. Otherwise, the intersection is determined, and the non-crossable singular configuration at the intersection point is determined; (4) solving the differential algebraic system of equations (DAE) of index 2 using the Runge–Kutta method; and (5) solving the optimization problem. The method is illustrated through examples.  相似文献   

18.
There are manufacturing applications where a tool needs to move along a prescribed path performing machining operations. An excellent application of this problem is found in the increasingly popular layered manufacturing (LM) methods, where the laser traces the profile of a layer by moving along the path while the laser turns on. The path is typically described by a sequence of curves. For the entire process, the tool must move along each curve exactly once. For typical paths, significant time may be wasted in the movement between the end point of one curve to the start point of the next one along which the laser is turned off. Normally, this non-cutting motion is a straight-line motion so to minimize the distance. A good process plan would minimize the time wasted on such motion. A maximum linear intersection (MLI) algorithm is proposed to solve this problem. Next, we present a variation of the GA based method to solve it. We compare the performance of these two techniques, both in terms of jumping distance and the computing time requirement, with a view to their application to real-time path planning in LM applications.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号