arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1911.08511cs.CVeess.IV
收藏

基于体运动表示的动作识别

Action Recognition Using Volumetric Motion Representations

Johns Hopkins University(约翰斯·霍普金斯大学)

Michael Peven, Gregory D. Hager, Austin Reiter

摘要:

传统的动作识别模型是围绕二维透视图像的范式构建的。虽然复杂的时间序列模型推动了该领域的发展,但由于将域限制在2D范围内,许多信息仍然没有得到利用。在这项工作中,我们引入了一种新的运动表示为体素化的3D矢量场,并演示了如何使用它来提高动作识别网络的性能。这种体积表示非常适合3D CNN,并且允许在这些网络的训练期间使用面外数据增强技术。从RGB-D视频的这种表示的构造和推理都可以实时的运行。我们在开源NTU RGB+D数据集上使用这种表示与我们的网络设计展示了优越的结果,在这两个定义的评估指标上都优于最先进的技术。此外,我们通过实验展示了平面外增强技术如何创建视点不变性,并允许使用这种表示训练的模型推广到看不见的相机角度。代码可在这里:https://github.com/mpeven/ntu_rgb.

英文摘要:

Traditional action recognition models are constructed around the paradigm of 2D perspective imagery. Though sophisticated time-series models have pushed the field forward, much of the information is still not exploited by confining the domain to 2D. In this work, we introduce a novel representation of motion as a voxelized 3D vector field and demonstrate how it can be used to improve performance of action recognition networks. This volumetric representation is a natural fit for 3D CNNs, and allows out-of-plane data augmentation techniques during training of these networks. Both the construction of this representation from RGB-D video and inference can be run in real time. We demonstrate superior results using this representation with our network design on the open-source NTU RGB+D dataset where it outperforms state-of-the-art on both of the defined evaluation metrics. Furthermore, we experimentally show how the out-of-plane augmentation techniques create viewpoint invariance and allow the model trained using this representation to generalize to unseen camera angles. Code is available here: https://github.com/mpeven/ntu_rgb.

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。

↑