arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1905.09043cs.CV
收藏

基于成对匹配的鲁棒运动分割

Robust Motion Segmentation from Pairwise Matches

Czech Institute of Informatics, Robotics and Cybernetics – Czech Technical University in Prague(捷克信息学、机器人与控制论研究所——布拉格捷克理工大学)

Federica Arrigoni, Tomas Pajdla

摘要:

在本文中,我们解决了一个分类问题,以前没有考虑过,即运动分割只给成对匹配。我们的贡献,这一未探索的任务是一个新的制定运动分割作为一个两步的过程。首先,对图像对独立地执行运动分割。其次,我们将独立的成对分割结果以鲁棒的方式组合到最终的全局一致分割中。我们的方法受到平均方法成功的启发。我们在模拟以及在真实的实验中证明,我们的方法是非常有效的,在减少成对运动分割的错误,可以应付大量的不匹配。

英文摘要:

In this paper we address a classification problem that has not been considered before, namely motion segmentation given pairwise matches only. Our contribution to this unexplored task is a novel formulation of motion segmentation as a two-step process. First, motion segmentation is performed on image pairs independently. Secondly, we combine independent pairwise segmentation results in a robust way into the final globally consistent segmentation. Our approach is inspired by the success of averaging methods. We demonstrate in simulated as well as in real experiments that our method is very effective in reducing the errors in the pairwise motion segmentation and can cope with large number of mismatches.

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。

↑