首页> 外文期刊>IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics >Detecting 3-D motion field from range image sequences
【24h】

Detecting 3-D motion field from range image sequences

机译:从距离图像序列检测3-D运动场

获取原文
获取原文并翻译 | 示例

摘要

An algorithm for computing three-dimensional (3-D) velocity fieldnand motion parameters from a range image sequence is presented. It isnbased on a new integral 3-D rigid motion invariant feature-the trace ofna 3×3 “feature matrix” related to the moment ofninertia tensor. This trace can be computed at every point of a movingnsurface and provides a quantitative measure of the local shape of thensurface. Based on the feature's conservation along the trajectory ofnevery moving point, a 3-D Flow Constraint Equation is formulated andnsolved for the velocity field. The robustness of the feature in presencenof noise and discontinuity is analyzed
机译:提出了一种从距离图像序列中计算三维(3-D)速度场和运动参数的算法。它基于新的积分3D刚性运动不变特征-与神经张力张量有关的3×3“特征矩阵”的轨迹。可以在运动表面的每个点上计算此轨迹,并提供对表面局部形状的定量度量。基于沿每个运动点的轨迹的特征守恒性,针对速度场公式化并求解了3-D流动约束方程。分析了存在噪声和不连续性时特征的鲁棒性

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号