Paper Search Console

Home Search Page About Contact

Journal Title

Title of Journal: Vis Comput

Search In Journal Title:

Abbravation: The Visual Computer

Search In Journal Abbravation:

Publisher

Springer-Verlag

Search In Publisher:

DOI

10.1007/s00572-016-0745-9

Search In DOI:

ISSN

1432-2315

Search In ISSN:
Search In Title Of Papers:

Optimizationbased key frame extraction for motion

Authors: Xianmei Liu Aimin Hao Dan Zhao
Publish Date: 2012/03/10
Volume: 29, Issue: 1, Pages: 85-95
PDF Link

Abstract

In this paper we present a new solution for extracting key frames from motion capture data using an optimization algorithm to obtain compact and sparse key frame data that can represent the original dense human body motion capture animation The use of the genetic algorithm helps determine the optimal solution with global exploration capability while the use of a probabilistic simplex method helps expedite the speed of convergence By finding the chromosome that maximizes the fitness function the algorithm provides the optimal number of key frames as well as the low reconstruction error with an ordinary interpolation technique The reconstruction error is computed between the original motion and the reconstruction one by the weighted differences of joint positions and velocities The resulting set of key frames is obtained by iterative application of the algorithm with initial populations generated randomly and intelligently We also present experiments which demonstrate that the method can effectively extract key frames with a high compression ratio and reconstruct all other non key frames with high qualityThis work is supported and funded by the State Key Program of National Natural Science of China No 60533070 the Special Foundation of the “211 Project” Subject Construction for Young Researcher at the Beijing University of Technology the Beijing Municipal Commission of Education of Science and Technology Program No KM200910005020 We would like to acknowledge the help of the CMU Graphics Lab who provided us with the human motion capture data We also would like to thank the anonymous reviewers for their helpful comments and suggestions


Keywords:

References


.
Search In Abstract Of Papers:
Other Papers In This Journal:

  1. Interactive GPU-based adaptive cartoon-style rendering
  2. A bag-of-semantics model for image clustering
  3. Pose analysis using spectral geometry
  4. A SIMD-efficient 14 instruction shader program for high-throughput microtriangle rasterization
  5. Erratum to: Dynamic BFECC Characteristic Mapping method for fluid simulations
  6. Cyberworlds: architecture and modeling by an incrementally modular abstraction hierarchy
  7. Cyberworlds: architecture and modeling by an incrementally modular abstraction hierarchy
  8. Achieving developability of a polygonal surface by minimum deformation: a study of global and local optimization approaches
  9. Discriminative Hough context model for object detection
  10. Sampling-sensitive multiresolution hierarchy for irregular meshes
  11. Device-based decision-making for adaptation of three-dimensional content
  12. Selective rendering for efficient ray traced stereoscopic images
  13. An improved image analogy method based on adaptive CUDA-accelerated neighborhood matching framework
  14. Enriching a motion database by analogous combination of partial human motions
  15. Real-time EEG-based emotion monitoring using stable features
  16. Guiding flows for controlling crowds
  17. Geocube – GPU accelerated real-time rendering of transparency and translucency
  18. Illustrative uncertainty visualization of DTI fiber pathways
  19. An immersive multi-agent system for interactive applications
  20. A dynamic balanced flow for filtering point-sampled geometry
  21. Single-strips for fast interactive rendering
  22. Automatic blur-kernel-size estimation for motion deblurring
  23. Perceptually meaningful image editing

Search Result: