From canonical poses to 3D motion capture using a single camera.
- Fossati A Ecole Polytechnique Fédérale de Lausanne(EPFL)/IC/ISIM/CVLab, Computer Vision Laboratory, I&C Faculty,Station 14, CH-1015 Lausanne, Switzerland. andrea.fossati@epfl.ch
- Dimitrijevic M
- Lepetit V
- Fua P
- 2010-05-22
Published in:
- IEEE transactions on pattern analysis and machine intelligence. - 2010
Algorithms
Artificial Intelligence
Golf
Humans
Image Processing, Computer-Assisted
Motion
Normal Distribution
Posture
Video Recording
Walking
English
We combine detection and tracking techniques to achieve robust 3D motion recovery of people seen from arbitrary viewpoints by a single and potentially moving camera. We rely on detecting key postures, which can be done reliably, using a motion model to infer 3D poses between consecutive detections, and finally refining them over the whole sequence using a generative model. We demonstrate our approach in the cases of golf motions filmed using a static camera and walking motions acquired using a potentially moving one. We will show that our approach, although monocular, is both metrically accurate because it integrates information over many frames and robust because it can recover from a few misdetections.
- Language
-
- English
- Open access status
- green
- Identifiers
-
- DOI 10.1109/TPAMI.2009.108
- PMID 20489222
- Persistent URL
- https://folia.unifr.ch/global/documents/111916
Statistics
Document views: 30
File downloads:
- Full-text: 0