A Kinematic Chain Space for Monocular Motion Capture
A Kinematic Chain Space for Monocular Motion Capture
复制标题
DOI：
10.1007/978-3-030-11018-5_4
复制
发表时间：
2017-02
期刊：
影响因子：
--
通讯作者：
Bastian Wandt;H. Ackermann;B. Rosenhahn
中科院分区：
文献类型：
--
作者：
Bastian Wandt;H. Ackermann;B. Rosenhahn
本文研究了由未标定摄像机拍摄的单目图像序列中运动链(如人体骨骼)的运动捕获。我们提出了一种基于将观测投影到运动链空间(KCS)的方法。提出了一种优化的核范数，隐含地强制运动链的结构属性。与其他方法不同，我们的方法不依赖于训练数据或先前确定的约束条件，例如特定的身体长度。该算法能够重建几乎没有或几乎没有摄像机运动的场景，以及以前看不到的运动。它不仅适用于人类骨骼，还适用于其他运动链，如动物或工业机器人。我们在不同的基准数据库和现实世界场景上获得了最先进的结果。
This paper deals with motion capture of kinematic chains (eg human skeletons) from monocular image sequences taken by uncalibrated cameras. We present a method based on projecting an observation onto a kinematic chain space (KCS). An optimization of the nuclear norm is proposed that implicitly enforces structural properties of the kinematic chain. Unlike other approaches our method is not relying on training data or previously determined constraints such as particular body lengths. The proposed algorithm is able to reconstruct scenes with little or no camera motion and previously unseen motions. It is not only applicable to human skeletons but also to other kinematic chains for instance animals or industrial robots. We achieve state-of-the-art results on different benchmark databases and real world scenes.