Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs

By Timo von Marcard, Bodo Rosenhahn, Michael J. Black, Gerard Pons-Moll. Computer graphics forum (Print), 2017

369 citations recorded by the source corpus.

We address the problem of making human motion capture in the wild more practical by using a small set of inertial sensors attached to the body. Since the problem is heavily under‐constrained, previous methods either use a large number of sensors, which is intrusive, or they require additional video input. We take a different approach and constrain the problem by: (i) making use of a realistic statistical body model that includes anthropometric constraints and (ii) using a joint optimization framework to fit the model to orientation and acceleration measurements over multiple frames. The resulting tracker Sparse Inertial Poser (SIP) enables motion capture using only 6 sensors (attached to the wrists, lower legs, back and head) and works for arbitrary human motions. Experiments on the recently released TNT15 dataset show that, using the same number of sensors, SIP achieves higher accuracy than the dataset baseline without using any video data. We further demonstrate the effectiveness of SIP on newly recorded challenging motions in outdoor scenarios such as climbing or jumping over a wall.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/ddc994e001a4264b78a262732d7b6b96e7263f63

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

BodyNet: Volumetric Inference of 3D Human Body Shapes (2018, background): “3D human shape estimation has been mostly studied in controlled settings using speciﬁc sensors including multi-view capture [9], motion capture markers [10], inertial sensors [11], and 3D scanners [12].”
STAR: Sparse Trained Articulated Human Body Regressor (2020, background): “umber of shape parameters can be as high as 300 but most research uses only 10). This makes it useful to reason about 3D human body pose and shape given sparse measurements, such as IMU accelerations [11,12,26], sparse mocap markers [22,25] or 2D key points in images and videos [3,14,15,16,28,33,36,”
Learning to Estimate 3D Human Pose and Shape from a Single Color Image (2018, methodology): “The inherent ambiguity of the problem has forced the researchers to use monocular image sequences for inference [54, 3], employ multiple camera views [36, 16], or even explore alternative sensors, like Kinect [53] or IMUs [52].”
Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera (2018, methodology): “Eprior(θ) is chosen as defined in [42], enforcing θ to remain close to a multivariate Gaussian distribution of model poses and to stay within joint limits.”
ClothCap (2017, background): “Marcard et al. 2016, 2017) to facilitate the estimation of pose and the MCS with very baggy clothing.”
Using Inertial Sensors for Position and Orientation Estimation (2017, neutral): “In [152], the focus is instead on estimation of human motion using a much smaller amount”