Energy constraints on parameterized models
SIGGRAPH '87 Proceedings of the 14th annual conference on Computer graphics and interactive techniques
Video based human animation technique
MULTIMEDIA '99 Proceedings of the seventh ACM international conference on Multimedia (Part 1)
Reconstruction of articulated objects from point correspondences in a single uncalibrated image
Computer Vision and Image Understanding
Proceedings of the 2002 ACM SIGGRAPH/Eurographics symposium on Computer animation
A convex penalty method for optical human motion tracking
IWVS '03 First ACM SIGMM international workshop on Video surveillance
Application of inverse kinematics for skeleton manipulation in real-time
SCCG '03 Proceedings of the 19th spring conference on Computer graphics
Learning to track 3D human motion from silhouettes
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Interactive motion deformation with prioritized constraints
SCA '04 Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation
SCA '04 Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation
Modeling deformable human hands from medical images
SCA '04 Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation
Web3D '05 Proceedings of the tenth international conference on 3D Web technology
Human motion reconstruction from monocular images using genetic algorithms: Research Articles
Computer Animation and Virtual Worlds - Special Issue: The Very Best Papers from CASA 2004
Capture and synthesis of insect motion
Proceedings of the 2005 ACM SIGGRAPH/Eurographics symposium on Computer animation
Helping hand: an anatomically accurate inverse dynamics solution for unconstrained hand motion
Proceedings of the 2005 ACM SIGGRAPH/Eurographics symposium on Computer animation
Hi-index | 0.00 |
A model-based method is proposed in this paper for 3-dimensional human motion recovery, taking un-calibrated monocular data as input. Motion trend prediction is suggested to to recover smooth human motions with high efficiency; while its outputs are guaranteed to not only resemble the original motion from the same viewpoint the sequence was taken, but also look natural and reasonable from any given viewpoint. To evaluate the accuracy of reconstruction algorithm, the research program starts from "synthesized" input. Experiment carried on real video data will be discussed as well, which indicate that the proposed method is able to recover smooth human motions from their 2D image features with high accuracy.