@phdthesis{Huang:Thesis:2022,
  title = {Whole-Body Motion Capture and Beyond: From Model-Based Inference to Learning-Based Regression},
  abstract = {Though effective and successful, traditional marker-less Motion Capture (MoCap) methods suffer from several limitations: 1) they presume a character-specific body model, thus they do not permit a fully automatic pipeline and generalization over diverse body shapes; 2) no objects humans interact with are tracked, while in reality interaction between humans and objects is ubiquitous; 3) they heavily rely on a sophisticated optimization process, which needs a good initialization and strong priors. This process can be slow. We address all the aforementioned issues in this thesis, as described below. Firstly we propose a fully automatic method to accurately reconstruct a 3D human body from multi-view RGB videos, the typical setup for MoCap systems. We pre-process all RGB videos to obtain 2D keypoints and silhouettes. Then we fit the SMPL body model into the 2D measurements in two successive stages. In the first stage, the shape and pose parameters of SMPL are estimated frame-wise sequentially. In the second stage, a batch of frames are refined jointly with an extra DCT prior. Our method can naturally handle different body shapes and challenging poses without human intervention. Then we extend this system to support tracking of rigid objects the subjects interact with. Our setup consists of 6 Azure Kinect cameras. Firstly we pre-process all the videos by segmenting humans and objects and detecting 2D body joints. We adopt the SMPL-X model here to capture body and hand pose. The model is fitted to 2D keypoints and point clouds. Then the body poses and object poses are jointly updated with contact and interpenetration constraints. With this approach, we capture a novel human-object interaction dataset with natural RGB images and plausible body and object motion information. Lastly, we present the first practical and lightweight MoCap system that needs only 6 IMUs. Our approach is based on Bi-directional RNNs. The network can make use of temporal information by jointly reasoning about past and future IMU measurements. To handle the data scarcity issue, we create synthetic data from archival MoCap data. Overall, our system runs ten times faster than traditional optimization-based methods, and is numerically more accurate. We also show it is feasible to estimate which activity the subject is doing by only observing the IMU measurement from a smartwatch worn by the subject. This not only can be useful for a high-level semantic understanding of the human behavior, but also alarms the public of potential privacy concerns. In summary, we advance marker-less MoCap by contributing the first automatic yet accurate system, extending the MoCap methods to support rigid object tracking, and proposing a practical and lightweight algorithm via 6 IMUs. We believe our work makes marker-less and IMUs-based MoCap cheaper and more practical, thus closer to end-users for daily usage.},
  degree_type = {PhD},
  institution = {University of Tübingen},
  month = dec,
  year = {2022},
  slug = {huang-thesis-2022},
  author = {Huang, Yinghao},
  month_numeric = {12}
}