Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Outdoor Markerless Motion Capture with Sparse Handheld Video Cameras.

Yangang Wang, Yebin Liu, Xin Tong

    IEEE Transactions on Visualization and Computer Graphics
    |April 20, 2017
    PubMed
    Summary

    This study introduces a novel markerless motion capture method using only two handheld cameras for outdoor scenes. The technique enhances flexibility and broadens applications by effectively tracking 3D character poses.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    High-fidelity fast fluorescence lifetime imaging by event-based denoising.

    Nature biotechnology·2026
    Same author

    High numerical aperture confocal volumetric mesoscope reveals mesoscale subcellular dynamics in vivo.

    Nature biotechnology·2026
    Same author

    A gender-emotion interaction multi-task network for depression recognition via transformer-based multimodal fusion.

    Frontiers in psychiatry·2026
    Same author

    Real-time robust autofocus method enabling sustained intravital scanning light field imaging.

    Nature communications·2026
    Same author

    A multi-modal foundation model for brain disease diagnosis and medical imaging.

    Patterns (New York, N.Y.)·2026
    Same author

    Modulation of place cells using targeted stimulation with bidirectional microelectrode arrays enhances spatial learning speed in mice.

    Fundamental research·2026

    Area of Science:

    • Computer Vision
    • Robotics
    • Human-Computer Interaction

    Background:

    • Markerless motion capture is crucial for realistic character animation and human-computer interaction.
    • Existing methods often require controlled environments or multiple cameras, limiting outdoor applications.
    • Sparse handheld cameras offer flexibility but pose challenges for accurate 3D pose estimation.

    Purpose of the Study:

    • To develop an efficient and flexible markerless motion capture system for outdoor environments.
    • To enable accurate 3D character pose tracking using a minimal setup of sparse handheld cameras.
    • To overcome the limitations of existing methods in unconstrained, real-world scenarios.

    Main Methods:

    • A novel model-view consistency approach incorporating both foreground and background information.

    Related Experiment Videos

  • Modeling the background as a deformable 2D grid for consistency computation with sparse, moving cameras.
  • Employing a global-local optimization strategy with a new motion regularizer for robust 3D pose tracking.
  • Avoiding computationally intensive frame-by-frame video segmentation.

    • Main Results:

    • The proposed method successfully tracks 3D character poses in challenging outdoor settings with only two cameras.
    • Demonstrated superior performance compared to several alternative markerless motion capture techniques.
    • The background modeling and optimization approach effectively handles sparse camera views and motion.
    • The system achieves high flexibility in data capture, broadening potential applications.

    Conclusions:

    • The presented method offers a practical and effective solution for outdoor markerless motion capture.
    • The novel model-view consistency and background modeling significantly improve tracking accuracy with sparse cameras.
    • This approach paves the way for more accessible and versatile motion capture technologies.