• Corpus ID: 210990220

Full-body Performance Capture of Sports from Multi-view Video

@inproceedings{Bridgeman2019FullbodyPC,
  title={Full-body Performance Capture of Sports from Multi-view Video},
  author={Lewis Bridgeman},
  year={2019}
}
Full-body human performance capture has been extensively explored in constrained environments, but less attention has been applied to the task of performance capture in sports scenes. Sports datasets provide a wealth of challenges: player contact and occlusion; fast motion; and low resolution and wide-baseline cameras. We present a method that uses multiview pose to disambiguate players and overcome some of these issues. The applications are broad, including player performance analysis, sports… 
1 Citations

Figures from this paper

Assessment of deep learning pose estimates for sports collision tracking

The aim of this work is to evaluate the performance of a popular deep learning model “out of the box” for human pose estimation, on a dataset of ten staged rugby tackle movements performed in a marker-based motion capture laboratory with a system of three high-speed video cameras.

References

SHOWING 1-6 OF 6 REFERENCES

Multi-Person 3D Pose Estimation and Tracking in Sports

The proposed method achieves a significant improvement in speed over state-of-the-art methods and is believed to be the first method for full-body 3D pose estimation and tracking of multiple players in highly dynamic sports scenes.

Towards Accurate Marker-Less Human Shape and Pose Estimation over Time

  • Yinghao Huang
  • Computer Science
    2017 International Conference on 3D Vision (3DV)
  • 2017
This work presents a fully automatic method that, given multi-view videos, estimates 3D human pose and body shape and takes the recently proposed SMPLify method as the base method and extends it in several ways.

Learning to Estimate 3D Human Pose and Shape from a Single Color Image

This work addresses the problem of estimating the full body 3D human pose and shape from a single color image and proposes an efficient and effective direct prediction method based on ConvNets, incorporating a parametric statistical body shape model (SMPL) within an end-to-end framework.

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields

We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn

SMPL: a skinned multi-person linear model

The Skinned Multi-Person Linear model (SMPL) is a skinned vertex-based model that accurately represents a wide variety of body shapes in natural human poses that is compatible with existing graphics pipelines and iscompatible with existing rendering engines.

Joint Multi-Layer Segmentation and Reconstruction for Free-Viewpoint Video Applications

This paper proposes a technique which is able to efficiently compute a high-quality scene representation via graph-cut optimisation of an energy function combining multiple image cues with strong priors in a view-dependent manner with respect to each input camera.