Abstract
We address how human pose in 3-D can be recovered visually from multiple images captured at a number of locations. A scheme is proposed that transforms the multi-view data to a pose solution in a way that a number of constraints, are put together to identify the most probable pose. The scheme involves firstly the learning of the manifolds from training data, and a mapping process kicks in to pick up the right manifold from the library. Experiments show that the approach could successfully handle scenes of a variety of activities, and multi-view data do help improve the precision of pose estimation in a remarkable way.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
