arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.00136cs.CV
收藏

它在移动!运动摄像机视频中因果运动分割的概率模型

It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos

University of Massachusetts, Amherst(马萨诸塞大学阿默斯特分校)

Pia Bideau, Erik Learned-Miller

摘要:

人类检测和分割移动物体的能力在存在多个物体、复杂背景几何形状、观察者运动甚至伪装的情况下都有效。除此之外,检测运动的能力几乎是瞬时的。虽然最近在运动分割方面取得了很大进展,但似乎我们离人类的能力还很远。在这项工作中,我们从第一原理推导出一个新的似然函数,用于评估给定物体的3D运动方向的光流矢量的概率。这种可能性使用光流的角度和幅度的新颖组合来最大化关于对象的真实运动的信息。使用这种新的可能性和几个创新的初始化,我们开发了一个运动分割算法,击败了当前最先进的方法,由一个大的利润。我们比较了五个国家的最先进的方法在两个既定的基准,和第三个新的数据集的动物,我们介绍了推动运动分割到一个新的水平。

英文摘要:

The human ability to detect and segment moving objects works in the presence of multiple objects, complex background geometry, motion of the observer, and even camouflage. In addition to all of this, the ability to detect motion is nearly instantaneous. While there has been much recent progress in motion segmentation, it still appears we are far from human capabilities. In this work, we derive from first principles a new likelihood function for assessing the probability of an optical flow vector given the 3D motion direction of an object. This likelihood uses a novel combination of the angle and magnitude of the optical flow to maximize the information about the true motions of objects. Using this new likelihood and several innovations in initialization, we develop a motion segmentation algorithm that beats current state-of-the-art methods by a large margin. We compare to five state-of-the-art methods on two established benchmarks, and a third new data set of camouflaged animals, which we introduce to push motion segmentation to the next level.

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。

↑