Accurate Realtime Full-body Motion Capture Using a Single Depth Camera
Accurate Realtime Full-body Motion Capture Using a Single Depth Camera
复制标题
DOI：
10.1145/2366145.2366207
复制
发表时间：
2012-11-01
影响因子：
6.2
通讯作者：
Chai, Jinxiang
中科院分区：
文献类型：
--
作者：
Wei, Xiaolin;Zhang, Peizhao;Chai, Jinxiang
我们提出了一种快速，自动的方法，准确地捕捉全身运动数据，使用一个单一的深度相机。在我们的系统的核心在于一个实时注册过程，准确地重建3D人体姿势从单目深度图像，即使在严重的闭塞的情况下。我们的想法是制定的最大后验概率（MAP）框架中的注册问题，并通过线性系统求解器迭代注册的3D铰接人体模型与单眼深度线索。我们将深度数据，轮廓信息，全身几何形状，时间姿态先验和遮挡推理集成到一个统一的MAP估计框架中。然而，我们的3D跟踪过程需要手动初始化和故障恢复。我们通过将3D跟踪与3D姿态检测相结合来解决这一挑战。这种组合不仅使整个过程自动化，而且还显著提高了系统的鲁棒性和准确性。我们的整个算法是高度并行的，因此很容易在GPU上实现。我们通过在真实的时间内捕捉各种人体运动来展示我们方法的强大功能，并在与Kinect [2012]等替代系统的比较中实现最先进的准确性。
We present a fast, automatic method for accurately capturing full-body motion data using a single depth camera. At the core of our system lies a realtime registration process that accurately reconstructs 3D human poses from single monocular depth images, even in the case of significant occlusions. The idea is to formulate the registration problem in a Maximum A Posteriori (MAP) framework and iteratively register a 3D articulated human body model with monocular depth cues via linear system solvers. We integrate depth data, silhouette information, full-body geometry, temporal pose priors, and occlusion reasoning into a unified MAP estimation framework. Our 3D tracking process, however, requires manual initialization and recovery from failures. We address this challenge by combining 3D tracking with 3D pose detection. This combination not only automates the whole process but also significantly improves the robustness and accuracy of the system. Our whole algorithm is highly parallel and is therefore easily implemented on a GPU. We demonstrate the power of our approach by capturing a wide range of human movements in real time and achieve state-of-the-art accuracy in our comparison against alternative systems such as Kinect [2012].