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 1012.2138cs.CV
收藏

使用多个六点插值的稀疏运动分割

Sparse motion segmentation using multiple six-point consistencies

Linköping University(林雪平大学)

Vasileios Zografos, Klas Nordberg, Liam Ellis

摘要:

我们提出了一种方法,用于分割图像序列中的任意数量的移动对象,使用6点的几何形状在2D推断运动的一致性。该方法已在霍普金斯155数据库上进行了评估,并超过了目前最先进的方法,如SSC,无论是在两个和三个运动的整体性能,但也在最大误差方面。该方法的工作原理是在空间域中找到初始聚类,然后将每个剩余的点分类为属于最小化运动一致性得分的聚类。与大多数其他基于仿射相机模型的运动分割方法相比,所提出的方法是完全投影的。

英文摘要:

We present a method for segmenting an arbitrary number of moving objects in image sequences using the geometry of 6 points in 2D to infer motion consistency. The method has been evaluated on the Hopkins 155 database and surpasses current state-of-the-art methods such as SSC, both in terms of overall performance on two and three motions but also in terms of maximum errors. The method works by finding initial clusters in the spatial domain, and then classifying each remaining point as belonging to the cluster that minimizes a motion consistency score. In contrast to most other motion segmentation methods that are based on an affine camera model, the proposed method is fully projective.

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。

↑