Real-time and Markerless 3D Human Motion Capture using Multiple Views - Archive ouverte HAL Access content directly
Conference Papers Year : 2007

Real-time and Markerless 3D Human Motion Capture using Multiple Views

Abstract

We present a fully automated system for real-time and markerless 3D human motion capture. Our process is based on fast algorithms, uses simple techniques and requires low cost devices. Using input from multiple calibrated webcams, an extended "Shape from Silhouette" algorithm reconstructs the person in real-time. Fasts 3D shape and 3D skin parts analysis provide a robust and real-time system for human full-body tracking. Animation skeleton and simple morphological constraints make easier the motion capture process. Thanks to fast and simple algorithms and low-cost cameras, our system is well suited for home entertainment device. Results on real video sequences with fast and complex movements, demonstrate our approach robustness.
No file

Dates and versions

hal-01611072 , version 1 (05-10-2017)

Identifiers

  • HAL Id : hal-01611072 , version 1

Cite

Brice Michoud, Erwan Guillou, Saïda Bouakaz. Real-time and Markerless 3D Human Motion Capture using Multiple Views. 2nd Human Motion Workshop, Oct 2007, Rio de Janeiro, Brazil. ⟨hal-01611072⟩
176 View
0 Download

Share

Gmail Mastodon Facebook X LinkedIn More