Abstract
The optical flow of humans is well known to be useful for the analysis of human action. Given this, we devise an optical flow algorithm specifically for human motion and show that it is superior to generic flow methods. Designing a method by hand is impractical, so we develop a new training database of image sequences with ground truth optical flow. For this we use a 3D model of the human body and motion capture data to synthesize realistic flow fields. We then train a convolutional neural network to estimate human flow fields from pairs of images. Since many applications in human motion analysis depend on speed, and we anticipate mobile applications, we base our method on SpyNet with several modifications. We demonstrate that our trained network is more accurate than a wide range of top methods on held-out test data and that it generalizes well to real image sequences. When combined with a person detector/tracker, the approach provides a full solution to the problem of 2D human flow estimation. Both the code and the dataset are available for research.
Abstract (translated)
众所周知,人的光流可用于分析人类行为。鉴于此,我们设计了一种专门用于人体运动的光流算法,并表明它优于通用流动方法。手工设计方法是不切实际的,因此我们开发了一个新的具有地面实况光流的图像序列训练数据库。为此,我们使用人体的3D模型和运动捕捉数据来合成真实的流场。然后,我们训练卷积神经网络来估计成对图像的人体流场。由于人体运动分析中的许多应用都依赖于速度,并且我们预计移动应用程序,我们的方法基于SpyNet进行了多次修改。我们证明了我们训练有素的网络比保持测试数据的各种顶级方法更准确,并且它可以很好地推广到真实的图像序列。当与人检测器/跟踪器结合时,该方法提供了对2D人流估计问题的完全解决方案。代码和数据集都可用于研究。
URL
https://arxiv.org/abs/1806.05666