arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.01392cs.CV
收藏

用于装配视频的细粒度活动识别

Fine-grained activity recognition for assembly videos

Johns Hopkins University(约翰斯·霍普金斯大学)

Jonathan D. Jones, Cathryn Cortesa, Amy Shelton, Barbara Landau, Sanjeev Khudanpur, Gregory D. Hager

摘要:

在本文中,我们解决的任务,识别装配动作的结构(例如,一件家具或玩具积木塔)是建立从一组原始对象。认识到全方位的组装行动需要感知的空间细节的水平,还没有尝试在行动识别文献的日期。我们扩展了细粒度的活动识别设置,以解决在其充分的一般性的任务,通过在一个单一的框架内统一的装配动作和运动学结构的装配动作识别。我们使用这个框架来开发一个通用的方法,从观察序列识别装配动作,以及观察功能,利用空间装配的特殊结构。最后,我们在两个应用程序驱动的数据源上对我们的方法进行了经验评估:(1)IKEA组装数据集,以及(2)块构建数据集。首先,我们的系统识别装配动作的平均帧的准确度为70%,平均归一化编辑距离为10%。第二,这需要细粒度的几何推理来区分组件,我们的系统达到了23%的平均归一化编辑距离-比以前的工作相对提高了69%。

英文摘要:

In this paper we address the task of recognizing assembly actions as a structure (e.g. a piece of furniture or a toy block tower) is built up from a set of primitive objects. Recognizing the full range of assembly actions requires perception at a level of spatial detail that has not been attempted in the action recognition literature to date. We extend the fine-grained activity recognition setting to address the task of assembly action recognition in its full generality by unifying assembly actions and kinematic structures within a single framework. We use this framework to develop a general method for recognizing assembly actions from observation sequences, along with observation features that take advantage of a spatial assembly's special structure. Finally, we evaluate our method empirically on two application-driven data sources: (1) An IKEA furniture-assembly dataset, and (2) A block-building dataset. On the first, our system recognizes assembly actions with an average framewise accuracy of 70% and an average normalized edit distance of 10%. On the second, which requires fine-grained geometric reasoning to distinguish between assemblies, our system attains an average normalized edit distance of 23% -- a relative improvement of 69% over prior work.

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。

↑