arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.08646cs.CV
收藏

Boundary Flow:一个无需运动训练就能预测边界运动的连体网络

Boundary Flow: A Siamese Network that Predicts Boundary Motion without Training on Motion

Oregon State University(俄勒冈州立大学)

Peng Lei, Fuxin Li, Sinisa Todorovic

摘要:

本文利用深度学习,研究了视频中的联合对象边界检测和边界运动估计问题,我们称之为边界流估计。边界流是一种重要的中级视觉线索,因为边界表征了对象的空间范围,并且流指示了对象的运动和相互作用。然而,大多数关于运动估计的先前工作集中于密集对象运动或可能不一定驻留在边界上的特征点。对于边界流估计,我们指定了一个新的全卷积暹罗网络(FCSN),它联合估计两个连续帧中的对象级边界。在两个帧的边界对应预测相同的FCSN与一个新的,非常规的反卷积方法。最后,边界流估计的改进与基于边缘波滤波。评估进行三个任务:边界检测视频,边界流估计,和光流估计。在边界检测方面,我们在基准VSB 100数据集上实现了最先进的性能。在边界流估计方面,我们在Sintel训练数据集上给出了第一个结果。对于光流估计,我们运行最近的方法CPMFlow,但在增强输入与我们的边界流匹配,并实现显着的性能改进的Sintel基准。

英文摘要:

Using deep learning, this paper addresses the problem of joint object boundary detection and boundary motion estimation in videos, which we named boundary flow estimation. Boundary flow is an important mid-level visual cue as boundaries characterize objects spatial extents, and the flow indicates objects motions and interactions. Yet, most prior work on motion estimation has focused on dense object motion or feature points that may not necessarily reside on boundaries. For boundary flow estimation, we specify a new fully convolutional Siamese network (FCSN) that jointly estimates object-level boundaries in two consecutive frames. Boundary correspondences in the two frames are predicted by the same FCSN with a new, unconventional deconvolution approach. Finally, the boundary flow estimate is improved with an edgelet-based filtering. Evaluation is conducted on three tasks: boundary detection in videos, boundary flow estimation, and optical flow estimation. On boundary detection, we achieve the state-of-the-art performance on the benchmark VSB100 dataset. On boundary flow estimation, we present the first results on the Sintel training dataset. For optical flow estimation, we run the recent approach CPMFlow but on the augmented input with our boundary-flow matches, and achieve significant performance improvement on the Sintel benchmark.

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。

↑