首页> 外文会议>International Conference on Scale-Space and PDE Methods in Computer Vision; 20050407-09; Hofgeismar(DE) >Discontinuity-Preserving Computation of Variational Optic Flow in Real-Time
【24h】

Discontinuity-Preserving Computation of Variational Optic Flow in Real-Time

机译:实时变化光学流的不连续性计算

获取原文
获取原文并翻译 | 示例
获取外文期刊封面目录资料

摘要

Variational methods are very popular for optic flow computation: They yield dense flow fields and perform well if they are adapted such that they respect discontinuities in the image sequence or the flow field. Unfortunately, this adaptation results in high computational complexity. In our paper we show that it is possible to achieve real-time performance for these methods if bidirectional multi-grid strategies are used. To this end, we study two prototypes: ⅰ) For the anisotropic image-driven technique of Nagel and Enkelmann that results in a linear system of equations we derive a regular full multigrid scheme, ⅱ) For an isotropic flow-driven approach with total variation (TV) regularisation that requires to solve a nonlinear system of equations we develop a full multigrid strategy based on a full approximation scheme (FAS). Experiments for sequences of size 160 x 120 demonstrate the excellent performance of the proposed numerical schemes. With frame rates of 6 and 12 dense flow fields per second, respectively, both implementations outperform corresponding modified explicit schemes by two to three orders of magnitude. Thus, for the first time ever, real-time performance can be achieved for these high quality methods.
机译:变分方法在光流计算中非常流行:它们产生密集的流场,并且如果适应性强,使其尊重图像序列或流场中的不连续性,则表现良好。不幸的是,这种适应导致很高的计算复杂度。在我们的论文中,我们表明,如果使用双向多网格策略,则可以实现这些方法的实时性能。为此,我们研究了两个原型:ⅰ)对于Nagel和Enkelmann的各向异性图像驱动技术,该技术产生了线性方程组,我们推导了规则的完全多重网格方案;ⅱ)对​​于具有总变化量的各向同性流驱动方法(TV)正则化需要解决一个非线性方程组,我们基于完全逼近方案(FAS)开发了一种完全多网格策略。大小为160 x 120的序列的实验证明了所提出的数值方案的出色性能。分别以每秒6个和12个密集流场的帧速率,这两种实现方式都比相应的修改的显式方案的性能高2到3个数量级。因此,有史以来第一次,这些高质量方法可以实现实时性能。

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