arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.03419cs.CV
收藏

上下文感知的人体运动预测

Context-aware Human Motion Prediction

Institut de Robòtica i Informàtica Industrial CSIC-UPC(西班牙国家研究委员会-加泰罗尼亚理工大学工业机器人与信息技术研究所)

Enric Corona, Albert Pumarola, Guillem Alenyà, Francesc Moreno-Noguer

摘要:

在机器人技术和计算机视觉中,根据一系列过去的观察结果预测人体运动是许多应用的核心问题。目前的最新技术将这个问题表述为序列到序列任务,其中3D骨架的历史数据为预测未来运动的递归神经网络(RNN)提供信息,通常为1到2秒。然而,迄今为止已经排除的一个方面是人类运动固有地由与环境中的对象和/或其他人类的交互驱动的事实。在本文中,我们探索这种情况下使用一种新的上下文感知的运动预测架构。我们使用一个语义图模型,其中的节点参数化的人和物体的场景和边缘的相互作用。这些交互通过图形注意层迭代学习,并提供过去的观察结果,现在包括对象和人体运动。一旦学习了这个语义图,我们就将其注入到标准RNN中,以预测人类和物体的未来移动。我们考虑我们的架构的两个变体,要么冻结上下文交互在未来更新它们。对“全身人体运动数据库”的彻底评估表明,在这两种情况下,我们的上下文感知网络的表现明显优于不考虑上下文信息的基线。

英文摘要:

The problem of predicting human motion given a sequence of past observations is at the core of many applications in robotics and computer vision. Current state-of-the-art formulate this problem as a sequence-to-sequence task, in which a historical of 3D skeletons feeds a Recurrent Neural Network (RNN) that predicts future movements, typically in the order of 1 to 2 seconds. However, one aspect that has been obviated so far, is the fact that human motion is inherently driven by interactions with objects and/or other humans in the environment. In this paper, we explore this scenario using a novel context-aware motion prediction architecture. We use a semantic-graph model where the nodes parameterize the human and objects in the scene and the edges their mutual interactions. These interactions are iteratively learned through a graph attention layer, fed with the past observations, which now include both object and human body motions. Once this semantic graph is learned, we inject it to a standard RNN to predict future movements of the human/s and object/s. We consider two variants of our architecture, either freezing the contextual interactions in the future of updating them. A thorough evaluation in the "Whole-Body Human Motion Database" shows that in both cases, our context-aware networks clearly outperform baselines in which the context information is not considered.

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。

↑