Perceiving Systems, Computer Vision

Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera

2018

Conference Paper

ps


In this work, we propose a method that combines a single hand-held camera and a set of Inertial Measurement Units (IMUs) attached at the body limbs to estimate accurate 3D poses in the wild. This poses many new challenges: the moving camera, heading drift, cluttered background, occlusions and many people visible in the video. We associate 2D pose detections in each image to the corresponding IMU-equipped persons by solving a novel graph based optimization problem that forces 3D to 2D coherency within a frame and across long range frames. Given associations, we jointly optimize the pose of a statistical body model, the camera pose and heading drift using a continuous optimization framework. We validated our method on the TotalCapture dataset, which provides video and IMU synchronized with ground truth. We obtain an accuracy of 26mm, which makes it accurate enough to serve as a benchmark for image-based 3D pose estimation in the wild. Using our method, we recorded 3D Poses in the Wild (3DPW ), a new dataset consisting of more than 51; 000 frames with accurate 3D pose in challenging sequences, including walking in the city, going up-stairs, having co ffee or taking the bus. We make the reconstructed 3D poses, video, IMU and 3D models available for research purposes at http://virtualhumans.mpi-inf.mpg.de/3DPW.

Author(s): Timo von Marcard and Roberto Henschel and Michael J. Black and Bodo Rosenhahn and Gerard Pons-Moll
Book Title: European Conference on Computer Vision (ECCV)
Volume: Lecture Notes in Computer Science, vol 11214
Pages: 614--631
Year: 2018
Month: September
Publisher: Springer, Cham

Department(s): Perceiving Systems
Research Project(s): IMU-based Human Motion Capture Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: https://doi.org/10.1007/978-3-030-01249-6_37
Event Place: Munich, Germany

ISBN: 978-3-030-01249-6

Links: pdf
SupMat
data
project

BibTex

@inproceedings{vip:eccv:2018,
  title = {Recovering Accurate {3D} Human Pose in The Wild Using {IMUs} and a Moving Camera},
  author = {von Marcard, Timo and Henschel, Roberto and Black, Michael J. and Rosenhahn, Bodo and Pons-Moll, Gerard},
  booktitle = {European Conference on Computer Vision (ECCV)},
  volume = {Lecture Notes in Computer Science, vol 11214},
  pages = {614--631},
  publisher = {Springer, Cham},
  month = sep,
  year = {2018},
  doi = {https://doi.org/10.1007/978-3-030-01249-6_37},
  month_numeric = {9}
}