arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1804.02142cs.CV
收藏

利用互补几何模型的运动分割

Motion Segmentation by Exploiting Complementary Geometric Models

National University of Singapore(新加坡国立大学);Intel Labs(英特尔实验室)

Xun Xu, Loong-Fah Cheong, Zhuwen Li

摘要:

许多真实世界的序列不能方便地分类为一般或退化;在这种情况下,在使用基本矩阵或单应性模型进行运动分割时强加错误的二分法将导致困难。即使我们面对的是一个一般的场景运动,基本的矩阵方法作为一个模型的运动分割仍然遭受了一些缺陷,我们在本文中讨论。只有我们明智地利用来自更简单的单应性模型的信息,才能实现基本矩阵方法的全部潜力。从这些考虑,我们提出了一个多视图谱聚类框架,协同结合多个模型在一起。我们表明,性能可以大大提高,以这种方式。我们对现有的运动分割数据集进行了广泛的测试,在所有这些数据集上都实现了最先进的性能;我们还提出了一个更现实和更具挑战性的数据集,该数据集改编自KITTI基准,包含传统数据集中看不到的真实效果,如强透视和强向前平移。

英文摘要:

Many real-world sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation would lead to difficulty. Even when we are confronted with a general scene-motion, the fundamental matrix approach as a model for motion segmentation still suffers from several defects, which we discuss in this paper. The full potential of the fundamental matrix approach could only be realized if we judiciously harness information from the simpler homography model. From these considerations, we propose a multi-view spectral clustering framework that synergistically combines multiple models together. We show that the performance can be substantially improved in this way. We perform extensive testing on existing motion segmentation datasets, achieving state-of-the-art performance on all of them; we also put forth a more realistic and challenging dataset adapted from the KITTI benchmark, containing real-world effects such as strong perspectives and strong forward translations not seen in the traditional datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑