Fast articulated motion tracking using a sums of Gaussians body model

Abstract

We present an approach for modeling the human body by Sums of spatial Gaussians (SoG), allowing us to perform fast and high-quality markerless motion capture from multi-view video sequences. The SoG model is equipped with a color model to represent the shape and appearance of the human and can be reconstructed from a sparse set of images. Similar to the human body, we also represent the image domain as SoG that models color consistent image blobs. Based on the SoG models of the image and the human body, we introduce a novel continuous and differentiable model-to-image similarity measure that can be used to estimate the skeletal motion of a human at 5-15 frames per second even for many camera views. In our experiments, we show that our method, which does not rely on silhouettes or training data, offers an good balance between accuracy and computational cost.

Real-Time Human Pose Tracking from Range Data

“…One class of existing approaches requires multiple cameras to constrain the pose of the tracked person [3], while our approach tracks with a single depth camera. Off-line multicamera approaches typically aim at achieving highly accurate pose reconstruction up to the surface mesh level [4] at the expense of long processing and inconvenient setups.…”

Real-Time Body Tracking with One Depth Camera and Inertial Sensors

“…3c. As opposed to Baak et al, we minimize d(M X , M I ) using a gradient descent solver similar to the one used in [14] and employ analytic derivatives.…”

Multiview foreground segmentation using 3D probabilistic model

“…The approaches in [1,11,14] require training data to learn either restrictive motion models or a mapping from image features to the 3D pose. In [16] the authors propose a rigid human body model that comprises a kinematic skeleton and an attached body approximation modeled as a Sum of Gaussians where 58 joints work together to model a detailed spine and clavicles. In [8] shape and motion retrieval are detected by means of EM framework to simultaneously update a set of volumetric voxel occupancy probabilities and retrieve a best estimate of the dense 3D motion field from the last consecutive frame set.…”