Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
10.1145/3180308.3180344acmconferencesArticle/Chapter ViewAbstractPublication PagesiuiConference Proceedingsconference-collections
poster

A Deep Learning Based Method For 3D Human Pose Estimation From 2D Fisheye Images

Published: 05 March 2018 Publication History

Abstract

We propose a deep learning based method to directly estimate the human joint positions in 3D space from 2D fisheye images captured in an egocentric manner. The core of our method is a novel network architecture based on Inception-v3 [4], featuring the asymmtric convolutional filter size, the long short-term memory module, and the anthropomorphic weights on the training loss. We demonstrate our method outperform state-of-the-art method under different tasks. Our method can be helpful to develop useful deep learning network for human-machine interaction and VR/AR applications.

References

[1]
Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long Short-Term Memory. Neural Comput. 9, 8 (Nov. 1997), 1735--1780.
[2]
Helge Rhodin, Christian Richardt, Dan Casas, Eldar Insafutdinov, Mohammad Shafiei, Hans-Peter Seidel, Bernt Schiele, and Christian Theobalt. 2016. EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras. ACM Trans. Graph. 35, 6, Article 162 (Nov. 2016), 11 pages.
[3]
J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, and A. Blake. 2011. Real-time Human Pose Recognition in Parts from Single Depth Images. In Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR '11). 1297--1304.
[4]
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2016. Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 2818--2826.

Cited By

View all
  • (2023)Centroid human tracking via oriented detection in overhead fisheye sequencesThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-023-02790-540:1(407-425)Online publication date: 17-Feb-2023

Index Terms

  1. A Deep Learning Based Method For 3D Human Pose Estimation From 2D Fisheye Images

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      IUI '18 Companion: Companion Proceedings of the 23rd International Conference on Intelligent User Interfaces
      March 2018
      141 pages
      ISBN:9781450355711
      DOI:10.1145/3180308
      Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 05 March 2018

      Check for updates

      Author Tags

      1. 3D Human Pose Estimation
      2. Anthropomorphic Weights
      3. Convolutional Neural Networks
      4. Egocentric View
      5. Fisheye Image

      Qualifiers

      • Poster
      • Research
      • Refereed limited

      Conference

      IUI'18
      Sponsor:

      Acceptance Rates

      IUI '18 Companion Paper Acceptance Rate 63 of 127 submissions, 50%;
      Overall Acceptance Rate 746 of 2,811 submissions, 27%

      Upcoming Conference

      IUI '25

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)3
      • Downloads (Last 6 weeks)0
      Reflects downloads up to 12 Sep 2024

      Other Metrics

      Citations

      Cited By

      View all
      • (2023)Centroid human tracking via oriented detection in overhead fisheye sequencesThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-023-02790-540:1(407-425)Online publication date: 17-Feb-2023

      View Options

      Get Access

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media