CoChat
Sign Up
Cited by 342Human Pose and Action RecognitionHuman Motion and Animation3D Shape Modeling and Analysis

The DOI matches its Crossref record; 72 of the 72 references it cites were found in a registry or an index.

Deep inertial poser: learning to reconstruct human pose from sparse inertial measurements in real time

Open access
Huang, Yinghao, Kaufmann, Manuel, Aksan, Emre, Black, Michael J., Hilliges, Otmar, Pons-Moll, Gerard·2018·ACM Transactions on Graphics
DOI 10.1145/3272127.3275108
Open this paper in CoChat — free accountOpen PDF

Abstract

We demonstrate a novel deep neural network capable of reconstructing human full body pose in real-time from 6 Inertial Measurement Units (IMUs) worn on the user's body. In doing so, we address several difficult challenges. First, the problem is severely under-constrained as multiple pose parameters produce the same IMU orientations. Second, capturing IMU data in conjunction with ground-truth poses is expensive and difficult to do in many target application scenarios (e.g., outdoors). Third, modeling temporal dependencies through non-linear optimization has proven effective in prior work but makes real-time prediction infeasible. To address this important limitation, we learn the temporal pose priors using deep learning. To learn from sufficient data, we synthesize IMU data from motion capture datasets. A bi-directional RNN architecture leverages past and future information that is available at training time. At test time, we deploy the network in a sliding window fashion, retaining real time capabilities. To evaluate our method, we recorded DIP-IMU, a dataset consisting of 10 subjects wearing 17 IMUs for validation in 64 sequences with 330 000 time instants; this constitutes the largest IMU dataset publicly available. We quantitatively evaluate our approach on multiple datasets and show results from a real-time implementation. DIP-IMU and the code are available for research purposes. 1

Overview

Integrity signals

Registry

Crossref · 10.1145/3272127.3275108

Cites

72 of 72 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 72 references

Research works printed but not linked: 11

  1. 2018. Unifying Motion Capture Datasets by Automatically Solving for Full-body Shape and Motion. In preparation ( 2018 ). 2018. Unifying Motion Capture Datasets by Automatically Solving for Full-body Shape and Motion. In preparation (2018).
  2. 10.5555/794191.794776 · DOI
  3. Zhe Cao , Tomas Simon , Shih-En Wei , and Yaser Sheikh . 2016. Realtime multi-person 2d pose estimation using part affinity fields. arXiv preprint arXiv:1611.08050 ( 2016 ). Zhe Cao, Tomas Simon, Shih-En Wei, and Yaser Sheikh. 2016. Realtime multi-person 2d pose estimation using part affinity fields. arXiv preprint arXiv:1611.08050 (2016). · arXiv
  4. 10.5555/2919332.2919834 · DOI
  5. Partha Ghosh , Jie Song , Emre Aksan , and Otmar Hilliges . 2017. Learning Human Motion Models for Long-term Predictions. arXiv preprint arXiv:1704.02827 ( 2017 ). Partha Ghosh, Jie Song, Emre Aksan, and Otmar Hilliges. 2017. Learning Human Motion Models for Long-term Predictions. arXiv preprint arXiv:1704.02827 (2017). · arXiv
  6. Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). · arXiv
  7. 10.5555/2354409.2354910 · DOI
  8. Daniel Roetenberg , Henk Luinge , and Per Slycke . 2007 . Moven: Full 6dof human motion tracking using miniature inertial sensors . Xsen Technologies , December (2007). Daniel Roetenberg, Henk Luinge, and Per Slycke. 2007. Moven: Full 6dof human motion tracking using miniature inertial sensors. Xsen Technologies, December (2007).
  9. Yu Tao , Zerong Zheng , Kaiwen Guo , Jianhui Zhao , Dai Quionhai , Hao Li , Gerard Pons-Moll , and Yebin Liu . 2018 . DoubleFusion: Real-time Capture of Human Performance with Inner Body Shape from a Depth Sensor , In IEEE Conf. on Computer Vision and Pattern Recognition. IEEE Conf. on Computer Vision and Pattern Recognition. CVPR Oral. Yu Tao, Zerong Zheng, Kaiwen Guo, Jianhui Zhao, Dai Quionhai, Hao Li, Gerard Pons-Moll, and Yebin Liu. 2018. DoubleFusion: Real-time Capture of Human Performance with Inner Body Shape from a Depth Sensor, In IEEE Conf. on Computer Vision and Pattern Recognition. IEEE Conf. on Computer Vision and Pattern Recognition. CVPR Oral.
  10. 10.5555/2354409.2354668 · DOI
  11. Jindong Wang , Yiqiang Chen , Shuji Hao , Xiaohui Peng , and Lisha Hu. 2017. Deep learning for sensor-based activity recognition: A survey. arXiv preprint arXiv:1707.03502 ( 2017 ). Jindong Wang, Yiqiang Chen, Shuji Hao, Xiaohui Peng, and Lisha Hu. 2017. Deep learning for sensor-based activity recognition: A survey. arXiv preprint arXiv:1707.03502 (2017). · arXiv

Cited by

Sorted by citations

Items 201–300 of 341

Related

See all

Metadata

Authors
Huang, Y., Kaufmann, M., Aksan, E., Black, M. J., Hilliges, O., & Pons-Moll, G.
Affiliations
  • Max Planck Institute for Intelligent Systems (DE)
  • ETH Zurich (CH)
  • Max Planck Institute for Informatics, Saarbrücken, Germany
ORCID
Venue
ACM Transactions on Graphics
Publisher
Association for Computing Machinery (ACM)
Published
2018-12-04
Volume
37
Issue
6
Pages
1-15
ISSN
  • 0730-0301 (ISSN-L)
  • 1557-7368
DOI
10.1145/3272127.3275108
OpenAlex
W2898073175
Cited by
342
References
72
Citations by year
2026: 43 · 2025: 54 · 2024: 69 · 2023: 56 · 2022: 38 · 2021: 44 · 2020: 26 · 2019: 12
FWCI
10.25
Type
journal article
Language
en
Open access
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
ACM Transactions on Graphics (publishedVersion)
Funders
  • Nvidia
  • H2020 European Research Council (717054)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
Keywords
inertial measurement unit, full-body pose estimation, real-time pose estimation, bidirectional recurrent neural network, motion capture, wearable sensors

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review