Motion Compression using Principal Geodesics Analysis

Maxime Tournier 1 Lionel Reveret 1 Xiaomao Wu 1 Nicolas Courty 2 Elise Arnaud 3
1 EVASION - Virtual environments for animation and image synthesis of natural objects
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
3 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We present a novel, lossy compression method for human motion data that exploits both temporal and spatial coherence. We first build a compact skeleton pose model from a single motion using Principal Geodesic Analysis (PGA). The key idea is to perform compression by only storing the model parameters along with the end-joints and root joint trajectories in the output data. The input data are recovered by optimizing PGA variables to match end-effectors positions in an inverse kinematics approach. Our experimental results show that considerable compression rates can be obtained using our method, with few reconstruction and perceptual errors. Thanks to the embedding of the pose model, our system can also be suitable for motion editing purposes.
Document type :
Poster communications
Complete list of metadatas

Cited literature [2 references]  Display  Hide  Download


https://hal.inria.fr/inria-00590253
Contributor : Team Perception <>
Submitted on : Tuesday, May 3, 2011 - 9:49:54 AM
Last modification on : Friday, July 12, 2019 - 1:17:01 AM
Long-term archiving on : Thursday, August 4, 2011 - 3:08:39 AM

Files

tournier08.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : inria-00590253, version 1

Citation

Maxime Tournier, Lionel Reveret, Xiaomao Wu, Nicolas Courty, Elise Arnaud. Motion Compression using Principal Geodesics Analysis. SCA '08 - ACM-SIGGRAPH/Eurographics Symposium on Computer Animation, Jul 2008, Dublin, Ireland. 2008. ⟨inria-00590253⟩

Share

Metrics

Record views

645

Files downloads

392