Hybrid approach for orientation-estimation of rotating humans in video frames acquired by stationary monocular camera

David Baumgartner, Christoph Praschl, Tobias Zucali, Gerald Adam Zwettler

Publikation: Beitrag in FachzeitschriftArtikelBegutachtung

2 Zitate (Scopus)

Abstract

The precise orientation-estimation of humans relative to the pose of a monocular camera system is a challenging task due to the general aspects of camera calibration and the deformable nature of a human body in motion. Thus, novel approaches of Deep Learning for precise object pose-estimation in robotics are hard to adapt to human body analysis. In this work, a hybrid approach for the accurate estimation of a human body rotation relative to a camera system is presented, thereby significantly improving results derived from poseNet by applying analysis of optical flow in a frame to frame comparison. The human body in-place rotating in T-pose is thereby aligned in the center, applying object tracking methods to compensate for translations of the body movement. After 2D skeleton extraction, the optical flow is calculated for a region of interest (ROI) area aligned relative to the vertical skeleton joint representing the spine and compared frame by frame. To evaluate the eligibility of the clothing as a fundament for good feature, the local pixel homogeneity is taken into consideration to restrict the optical flow to heterogeneous regions with distinctive features like imprint patterns, buttons or buckles besides local illumination changes. Based on the mean optical flow with a coarse approximation of the axial body shape as ellipsis, an accuracy between 0.1° and 2.0° by a target rotation of 10° for orientation-estimation is achieved on a frame-to-frame comparison evaluated and validated on both, Computer Generated Imagery (CGI) renderings and real-world videos of people wearing clothing of varying feature appropriateness.

OriginalspracheEnglisch
Seiten (von - bis)39-47
Seitenumfang9
FachzeitschriftJournal of WSCG
Jahrgang2020
Ausgabenummer2020
DOIs
PublikationsstatusVeröffentlicht - 2020
VeranstaltungInternational Conferences in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG) 2020 - Pilsen, Tschechische Republik
Dauer: 18 Mai 202022 Mai 2020
http://www.wscg.eu/

Schlagwörter

  • Object Tracking
  • Orientation-Estimation
  • Optical Flow
  • Image Alignment
  • Human Skeleton Extraction
  • Human Pose Estimation
  • Pixel Homogeneity

Fingerprint

Untersuchen Sie die Forschungsthemen von „Hybrid approach for orientation-estimation of rotating humans in video frames acquired by stationary monocular camera“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren