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 1610.05693cs.CV
收藏

长复杂操作动作序列的语义分解与识别

Semantic Decomposition and Recognition of Long and Complex Manipulation Action Sequences

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Georg-August-Universität Göttingen(格奥尔格-奥古斯特-哥廷根大学)

Eren Erdal Aksoy, Adil Orhan, Florentin Woergoetter

摘要:

在计算机视觉中,理解连续的人类动作是一个重要的问题。虽然存在着大量的工作在动作序列的识别,大多数方法遭受的问题,涉及运动,动作组合和场景上下文的巨大变化。在本文中,我们介绍了一种新的方法,语义分割和识别长而复杂的操作动作任务,如“准备早餐”或“做三明治”。我们表示操纵与我们最近推出的“语义事件链”(SEC)的概念,它捕获的基本时空结构的动作不变的运动,速度和场景上下文。仅基于提取的SEC中操纵对象和手之间的时空交互,该框架自动解析顺序或并发执行的各个操纵流。使用事件链,我们的方法进一步提取每个解析操作的基本原始元素。在不需要任何先验对象知识的情况下,所提出的框架还可以提取在语义上相似的操作中表现出相同作用的类对象场景实体。我们对最近的各种数据集进行了广泛的实验,以验证框架的鲁棒性。

英文摘要:

Understanding continuous human actions is a non-trivial but important problem in computer vision. Although there exists a large corpus of work in the recognition of action sequences, most approaches suffer from problems relating to vast variations in motions, action combinations, and scene contexts. In this paper, we introduce a novel method for semantic segmentation and recognition of long and complex manipulation action tasks, such as "preparing a breakfast" or "making a sandwich". We represent manipulations with our recently introduced "Semantic Event Chain" (SEC) concept, which captures the underlying spatiotemporal structure of an action invariant to motion, velocity, and scene context. Solely based on the spatiotemporal interactions between manipulated objects and hands in the extracted SEC, the framework automatically parses individual manipulation streams performed either sequentially or concurrently. Using event chains, our method further extracts basic primitive elements of each parsed manipulation. Without requiring any prior object knowledge, the proposed framework can also extract object-like scene entities that exhibit the same role in semantically similar manipulations. We conduct extensive experiments on various recent datasets to validate the robustness of the framework.

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。

↑